© 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. 10-RES_POST_32K-OAI
    11. 31146
    Prev
    Next
    INDEX
    Explanations

    content related to physical health and safety precautions

    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
    762
    +0.14
    0.7%
    747
    +0.10
    0.4%
    420
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.14
    0.28
    351
    +0.10
    0.15
    282
    +0.08
    0.14
    Negative Logits
     Revision
    -0.91
     Upgrade
    -0.85
     Franchise
    -0.83
     Dynasty
    -0.78
     Transcript
    -0.76
     Conversion
    -0.75
     revisions
    -0.75
     Loan
    -0.75
     Success
    -0.75
     Patent
    -0.75
    POSITIVE LOGITS
     cla
    1.43
     solitude
    1.24
     pedestrians
    1.24
     indoors
    1.22
     cramped
    1.21
     passers
    1.17
     strangers
    1.17
     trespass
    1.15
     outdoors
    1.14
     walking
    1.14
    Activations Density 8.427%

    No Known Activations