© 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. 26618
    Prev
    Next
    INDEX
    Explanations

    references to page numbers and citations in academic texts

    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
    314
    +0.17
    0.8%
    373
    +0.16
    0.7%
    196
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    196
    +0.17
    0.02
    316
    +0.16
    0.02
    655
    +0.12
    0.02
    Negative Logits
     jammed
    -0.66
     settled
    -0.64
     tuned
    -0.63
     Tinker
    -0.62
     perfected
    -0.61
     disapprove
    -0.61
     awoke
    -0.60
     trave
    -0.60
     administ
    -0.60
     rigged
    -0.60
    POSITIVE LOGITS
    xxx
    1.06
     xx
    1.02
    cit
    0.98
    xx
    0.96
    233
    0.92
     cx
    0.89
    166
    0.88
     cit
    0.85
    231
    0.85
    232
    0.85
    Activations Density 0.068%

    No Known Activations