© 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. 7818
    Prev
    Next
    INDEX
    Explanations

    mentions of ethical considerations

    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
    187
    +0.12
    0.6%
    724
    +0.12
    0.5%
    589
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.12
    0.02
    288
    +0.12
    0.02
    314
    +0.12
    0.00
    Negative Logits
     Sabb
    -0.77
     WARN
    -0.74
     warrants
    -0.72
     warrant
    -0.71
     revolving
    -0.68
     clearance
    -0.66
     Covenant
    -0.63
     Fellowship
    -0.62
     Cyber
    -0.61
     reporting
    -0.60
    POSITIVE LOGITS
    ylene
    1.12
    iop
    0.97
    nick
    0.95
    ivari
    0.95
    nom
    0.93
    anie
    0.93
    ania
    0.92
    ipl
    0.91
    tery
    0.91
    lers
    0.89
    Activations Density 0.075%

    No Known Activations