© 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. 8-RES_POST_32K-OAI
    11. 4120
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to player performance in sports

    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
    765
    +0.10
    0.5%
    741
    +0.10
    0.5%
    739
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.10
    0.01
    326
    +0.10
    0.02
    238
    +0.10
    0.02
    Negative Logits
    ozyg
    -0.84
    Premium
    -0.81
    verified
    -0.81
    jew
    -0.78
    ãĥķãĤ¡
    -0.76
    imen
    -0.75
    oppers
    -0.75
    maxwell
    -0.74
    thur
    -0.72
    lucent
    -0.71
    POSITIVE LOGITS
     FTA
    0.95
     STL
    0.83
     turnovers
    0.73
     PTS
    0.73
     INT
    0.72
     reluct
    0.69
     AST
    0.69
     NET
    0.68
     DISTR
    0.67
     PROC
    0.67
    Activations Density 0.089%

    No Known Activations