© 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. 28684
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal charges, specifically felonies and misdemeanors

    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
    288
    +0.14
    0.6%
    535
    +0.10
    0.5%
    408
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    628
    +0.14
    0.02
    288
    +0.10
    0.02
    575
    +0.10
    0.02
    Negative Logits
    atu
    -0.93
    ator
    -0.89
    efficients
    -0.87
    atorial
    -0.83
    paren
    -0.81
    obyl
    -0.79
    ators
    -0.76
     Nanto
    -0.75
    abeth
    -0.75
    este
    -0.74
    POSITIVE LOGITS
     punishable
    0.94
     convictions
    0.91
     charges
    0.90
     conviction
    0.88
     arrests
    0.87
     probation
    0.86
     warrant
    0.86
     charge
    0.85
     burglary
    0.83
     arrest
    0.83
    Activations Density 0.108%

    No Known Activations