© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 21267
    Prev
    Next
    INDEX
    Explanations

    JavaScript function definitions

    oai_token-act-pair · gpt-3.5-turbo

    function call expressions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥µ
    -0.78
    matical
    -0.72
    Reviewer
    -0.71
    tin
    -0.68
    ween
    -0.66
    matically
    -0.64
    bies
    -0.64
    Ĥª
    -0.64
     giveaways
    -0.62
    urally
    -0.62
    POSITIVE LOGITS
     =>
    1.02
     //[
    0.93
     ;
    0.92
     !=
    0.88
     {
    0.88
     ==
    0.88
     âĩ
    0.87
     };
    0.83
     {}
    0.82
    ^{
    0.82
    Activations Density 0.054%

    No Known Activations