© 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. 30498
    Prev
    Next
    INDEX
    Explanations

    references to facts, data, and statistical information

    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
    373
    +0.11
    0.5%
    233
    +0.10
    0.4%
    529
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    709
    +0.11
    0.16
    233
    +0.10
    0.16
    221
    +0.09
    0.12
    Negative Logits
    kefeller
    -0.59
     namely
    -0.50
    "},"
    -0.47
     nomine
    -0.44
    conservancy
    -0.44
     viz
    -0.43
    prus
    -0.42
     nodd
    -0.42
    absolutely
    -0.41
     acknow
    -0.40
    POSITIVE LOGITS
    ,
    1.48
    ,...
    1.29
    ?,
    1.26
    !,
    1.24
    ,,
    1.21
    *,
    1.16
    ,[
    1.16
    .,
    1.10
    +,
    1.07
    ,.
    1.03
    Activations Density 23.166%

    No Known Activations