© 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. 8869
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and court-related terminology

    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
    238
    +0.10
    0.4%
    420
    +0.10
    0.4%
    526
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.09
    476
    +0.10
    0.04
    350
    +0.09
    0.05
    Negative Logits
    natureconservancy
    -0.71
     reminders
    -0.70
     requests
    -0.69
     solicitation
    -0.69
     disclaim
    -0.68
    accompan
    -0.67
     envelope
    -0.66
     sidx
    -0.66
     cov
    -0.66
    76561
    -0.65
    POSITIVE LOGITS
     Court
    1.11
     tribunal
    1.09
     jury
    1.01
     Tribunal
    1.00
     court
    0.99
     Appeals
    0.95
     Supreme
    0.94
    Court
    0.91
    jud
    0.89
     courts
    0.89
    Activations Density 1.211%

    No Known Activations