© 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. 9-RES-JB
    11. 14327
    Prev
    Next
    INDEX
    Explanations

    computer code snippets containing loops and conditional statements

    oai_token-act-pair · gpt-3.5-turbo

    programming constructs and mathematical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     footprints
    -0.64
     complicit
    -0.60
     reactive
    -0.59
    .�
    -0.59
     disg
    -0.59
     respons
    -0.59
     collabor
    -0.59
     Mund
    -0.57
     superf
    -0.56
     accommod
    -0.56
    POSITIVE LOGITS
     &&
    1.43
     ||
    1.24
     !=
    1.21
    ){
    1.08
     ==
    1.08
    &&
    1.00
     <=
    0.93
     >=
    0.87
    ||
    0.85
     {
    0.83
    Activations Density 0.060%

    No Known Activations