© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5219
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Kragh Andersen."

    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
    373
    +0.17
    0.8%
    587
    +0.11
    0.5%
    526
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.17
    0.02
    103
    +0.11
    0.02
    305
    +0.10
    0.02
    Negative Logits
     Nevada
    -0.63
     sem
    -0.62
    Ĥ¬
    -0.61
    SEE
    -0.60
     dare
    -0.58
    WARD
    -0.58
     Kashmir
    -0.57
     mitigation
    -0.57
     Coyotes
    -0.57
    Ùĩ
    -0.57
    POSITIVE LOGITS
    umpy
    1.08
    umps
    1.01
    inker
    0.99
    anky
    0.99
    agged
    0.97
    ackers
    0.97
    unch
    0.96
    aden
    0.95
    idge
    0.95
    amped
    0.95
    Activations Density 0.031%

    No Known Activations