© 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. 32267
    Prev
    Next
    INDEX
    Explanations

    numerical statistics and scores related to sports events

    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
    258
    +0.10
    0.4%
    97
    +0.09
    0.4%
    404
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.10
    0.04
    260
    +0.09
    0.04
    238
    +0.09
    0.03
    Negative Logits
    ebin
    -0.79
     bott
    -0.70
    eus
    -0.68
    netflix
    -0.67
     dinners
    -0.66
    peria
    -0.64
    rawdownloadcloneembedreportprint
    -0.63
    roid
    -0.63
    mentioned
    -0.63
    hub
    -0.62
    POSITIVE LOGITS
     seconds
    0.84
    th
    0.82
    veland
    0.81
     yards
    0.79
     unanswered
    0.79
    yards
    0.79
     MPH
    0.78
    seconds
    0.76
    aders
    0.74
     feet
    0.73
    Activations Density 0.202%

    No Known Activations