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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 8230
    Prev
    Next
    INDEX
    Explanations

    parentheses and punctuation marks, specifically focusing on their usage in news reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    185
    +0.09
    0.4%
    385
    +0.09
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    185
    +0.09
    0.03
    179
    +0.09
    0.03
    373
    +0.09
    -0.01
    Negative Logits
    oooooooooooooooo
    -0.72
    ãĥł
    -0.69
    ////////////////
    -0.69
     spoiler
    -0.67
    zu
    -0.65
    pex
    -0.65
     lighthouse
    -0.63
    agram
    -0.63
     conversions
    -0.61
    (*
    -0.61
    POSITIVE LOGITS
     WATCHED
    0.89
     Voters
    0.77
     Saying
    0.73
     Protesters
    0.69
    tty
    0.68
     Instead
    0.68
     Thousands
    0.65
     Speaking
    0.65
     Earlier
    0.63
     Dozens
    0.63
    Activations Density 0.197%

    No Known Activations