© 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. 10-RES_POST_32K-OAI
    11. 28067
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuation, specifically periods and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    640
    +0.16
    0.7%
    314
    +0.15
    0.7%
    373
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.16
    0.33
    145
    +0.15
    0.31
    440
    +0.13
    0.25
    Negative Logits
     Shoals
    -0.62
     thous
    -0.59
     Prosecut
    -0.58
     Canaver
    -0.57
     Skydragon
    -0.55
     welf
    -0.54
    ruciating
    -0.54
     allege
    -0.54
    ensibly
    -0.53
     oun
    -0.53
    POSITIVE LOGITS
    <|endoftext|>
    1.08
    Finally
    1.07
    SPONSORED
    1.06
    Lastly
    1.01
    Conclusion
    0.97
    ↵
    0.96
    ↵↵
    0.96
    Read
    0.95
    ↵Âł
    0.94
    ********************************
    0.92
    Activations Density 2.035%

    No Known Activations