© 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. 28395
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming or computer science

    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
    431
    +0.10
    0.4%
    731
    +0.10
    0.4%
    445
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    158
    +0.10
    0.01
    326
    +0.10
    0.02
    284
    +0.09
    0.01
    Negative Logits
     Reyn
    -0.78
     unintention
    -0.69
     Daly
    -0.68
    arts
    -0.68
    irin
    -0.67
    ĸļ
    -0.67
    ikuman
    -0.66
     silhou
    -0.65
    senal
    -0.64
     inexper
    -0.63
    POSITIVE LOGITS
    natureconservancy
    0.91
    /
    0.89
     Activate
    0.78
    here
    0.76
    \
    0.74
    else
    0.73
     ->
    0.72
    endif
    0.72
    ":["
    0.69
    ########
    0.67
    Activations Density 0.048%

    No Known Activations