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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 12186
    Prev
    Next
    INDEX
    Explanations

    words related to the prefix "syc" followed by vowels

    oai_token-act-pair · gpt-3.5-turbo

    words related to psychology or mental health concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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

    Negative Logits
     Collider
    -0.72
     largeDownload
    -0.62
     fodder
    -0.62
    Magikarp
    -0.62
     Byrd
    -0.61
     gorilla
    -0.61
     shin
    -0.60
     quir
    -0.60
     circulation
    -0.60
     ado
    -0.60
    POSITIVE LOGITS
    abus
    0.87
    Synopsis
    0.85
    esthesia
    0.83
    athetic
    0.77
    hetic
    0.77
    achus
    0.74
    ronic
    0.73
    Ü
    0.72
    oslav
    0.71
    rex
    0.70
    Activations Density 0.106%

    No Known Activations