© 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 EvalsExportsAPI 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. 28337
    Prev
    Next
    INDEX
    Explanations

    references to Supreme Court decisions and legal rulings

    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
    373
    +0.11
    0.5%
    121
    +0.10
    0.5%
    6
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.11
    0.03
    631
    +0.10
    0.03
    604
    +0.10
    0.03
    Negative Logits
    soDeliveryDate
    -0.77
    ashtra
    -0.73
    wcs
    -0.72
    anyahu
    -0.71
    anmar
    -0.70
    yout
    -0.69
     suspic
    -0.69
     destro
    -0.69
    uda
    -0.68
    rss
    -0.68
    POSITIVE LOGITS
     McCull
    1.00
     Tinker
    0.98
     Buckley
    0.97
     Reynolds
    0.97
     NAACP
    0.96
     Slaughter
    0.95
     Ply
    0.95
     Heller
    0.94
     id
    0.94
     Casey
    0.94
    Activations Density 0.357%

    No Known Activations