© 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. 26972
    Prev
    Next
    INDEX
    Explanations

    references to individuals or entities with the initial "M."

    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
    675
    +0.10
    0.4%
    671
    +0.09
    0.4%
    297
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.09
    314
    +0.09
    0.00
    103
    +0.09
    0.04
    Negative Logits
     needles
    -0.66
    ices
    -0.65
     emphasis
    -0.63
     Paste
    -0.63
     Supplement
    -0.62
    Score
    -0.61
     containment
    -0.60
    é¾įåĸļ士
    -0.58
    pload
    -0.58
    emic
    -0.58
    POSITIVE LOGITS
    Gov
    0.85
    oti
    0.82
    bly
    0.77
    planned
    0.75
    uly
    0.74
    una
    0.71
    bek
    0.71
    uda
    0.70
    ulk
    0.70
    hol
    0.70
    Activations Density 0.493%

    No Known Activations