© 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. 27287
    Prev
    Next
    INDEX
    Explanations

    instances of parentheses and similar punctuation 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
    513
    +0.13
    0.6%
    141
    +0.10
    0.5%
    52
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.13
    0.05
    627
    +0.10
    0.02
    314
    +0.10
    0.00
    Negative Logits
    cases
    -0.74
    azines
    -0.71
    theless
    -0.71
    fires
    -0.67
    iety
    -0.66
     calendars
    -0.66
     weddings
    -0.65
    facts
    -0.65
    stores
    -0.65
    Examples
    -0.65
    POSITIVE LOGITS
    ombat
    0.81
    talk
    0.78
     unsigned
    0.75
     ç¥ŀ
    0.73
     Rodrigo
    0.69
     Gab
    0.69
    76561
    0.67
    à
    0.67
     %%
    0.66
     Nathaniel
    0.66
    Activations Density 0.203%

    No Known Activations