© 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. 27887
    Prev
    Next
    INDEX
    Explanations

    actions related to legal processes and decision-making

    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
    308
    +0.10
    0.4%
    671
    +0.09
    0.4%
    53
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    611
    +0.10
    0.10
    665
    +0.09
    0.12
    70
    +0.09
    0.12
    Negative Logits
    hene
    -0.77
    Interstitial
    -0.70
    obyl
    -0.70
     ancest
    -0.69
    Merit
    -0.69
    timer
    -0.67
    bies
    -0.66
    wcsstore
    -0.64
    clair
    -0.63
     someday
    -0.63
    POSITIVE LOGITS
     him
    0.96
     Yates
    0.72
     McN
    0.69
     them
    0.68
    ģ«
    0.67
     Weeks
    0.66
    Attempts
    0.63
     Jacobs
    0.62
     permission
    0.62
     several
    0.60
    Activations Density 1.982%

    No Known Activations