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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 2401
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    mathematical symbols and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cringe
    -0.78
     chats
    -0.75
     flashbacks
    -0.71
     kios
    -0.70
     menus
    -0.70
     Skype
    -0.70
     authorization
    -0.69
     invitations
    -0.68
     mandatory
    -0.68
     chat
    -0.68
    POSITIVE LOGITS
    ^{
    1.65
    _{
    1.48
    \)
    1.44
     {\
    1.39
    +(
    1.39
    âĪĴ
    1.39
    $$
    1.37
    /(
    1.33
    )=
    1.31
     âĪĴ
    1.29
    Activations Density 0.082%

    No Known Activations