Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 6144
    5. 8-RES_FS6144-JB
    6. 1806
    Prev
    Next
    INDEX
    Explanations

    phrases related to establishment or initiation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    612
    +0.11
    0.5%
    665
    +0.11
    0.5%
    642
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    642
    +0.11
    0.04
    665
    +0.11
    0.05
    101
    +0.11
    0.05
    Negative Logits
    âĨij
    -0.78
    webkit
    -0.74
    obe
    -0.68
    govtrack
    -0.67
    iev
    -0.63
    bole
    -0.63
    umin
    -0.61
    wr
    -0.61
    ranged
    -0.60
    ffect
    -0.58
    POSITIVE LOGITS
     alliances
    1.04
     anew
    1.01
     friendships
    0.97
     rapport
    0.97
     partnerships
    0.95
     relationships
    0.82
     settlements
    0.80
    eers
    0.78
    eering
    0.77
    ablished
    0.76
    Activations Density 0.353%

    No Known Activations