© 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. 8839
    Prev
    Next
    INDEX
    Explanations

    names and identifiers related to players or athletes, specifically with the mention of "Hig."

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    178
    +0.09
    0.4%
    526
    +0.09
    0.4%
    149
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.09
    0.06
    352
    +0.09
    0.06
    254
    +0.09
    0.05
    Negative Logits
    é¾įå¥ij士
    -0.80
    FE
    -0.69
     Franch
    -0.68
    OPLE
    -0.67
    Ø©
    -0.67
     Harmon
    -0.66
    FORM
    -0.65
    代
    -0.64
     Savage
    -0.62
     PDT
    -0.61
    POSITIVE LOGITS
    emouth
    0.99
    akens
    0.94
    etics
    0.93
    gments
    0.92
    ´
    0.90
    ysis
    0.89
    Ŀ
    0.87
    emaker
    0.86
    osure
    0.86
    edly
    0.86
    Activations Density 0.257%

    No Known Activations