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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 7740
    Prev
    Next
    INDEX
    Explanations

    numerical terms indicating a sequence of actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe restrictions or limitations on actions

    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
     defe
    -0.76
    ãĤ´ãĥ³
    -0.74
     Sovere
    -0.66
     Vi
    -0.56
     unseen
    -0.55
    FI
    -0.54
     ze
    -0.53
     Governments
    -0.53
    WHERE
    -0.53
    FACE
    -0.52
    POSITIVE LOGITS
     apiece
    1.70
     per
    1.10
    poons
    1.06
    each
    1.03
     each
    1.01
     worth
    0.98
    illion
    0.97
     consecut
    0.97
    dozen
    0.96
    secut
    0.95
    Activations Density 0.583%

    No Known Activations