© 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. 30750
    Prev
    Next
    INDEX
    Explanations

    actions and events related to danger or accidents

    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
    347
    +0.11
    0.5%
    170
    +0.10
    0.5%
    182
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.11
    0.08
    761
    +0.10
    0.07
    469
    +0.10
    0.07
    Negative Logits
    ratom
    -0.77
    aird
    -0.74
    sbm
    -0.73
    ardless
    -0.73
    xual
    -0.71
    enegger
    -0.69
    ovember
    -0.67
    anmar
    -0.67
    ĸļ
    -0.67
    ombo
    -0.66
    POSITIVE LOGITS
     malfunction
    1.04
     overhe
    0.88
     unexpectedly
    0.83
     jammed
    0.82
     malf
    0.81
     omin
    0.76
     transmitting
    0.76
     abnorm
    0.72
     dangerously
    0.71
     snag
    0.71
    Activations Density 1.086%

    No Known Activations