© 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. 8-RES_POST_32K-OAI
    11. 6279
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "how" or "does."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    218
    +0.15
    0.7%
    360
    +0.12
    0.5%
    210
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    218
    +0.15
    0.03
    60
    +0.12
    0.03
    449
    +0.11
    0.03
    Negative Logits
    tracks
    -0.88
    pez
    -0.81
    crow
    -0.78
    isphere
    -0.76
    bags
    -0.76
    abouts
    -0.75
    ãĥ¯ãĥ³
    -0.72
    itud
    -0.71
    utical
    -0.71
    gs
    -0.71
    POSITIVE LOGITS
     anyone
    0.84
     anybody
    0.75
     fate
    0.64
     someone
    0.62
     he
    0.59
     turnover
    0.59
     appell
    0.57
    berra
    0.57
     reality
    0.57
     militar
    0.56
    Activations Density 0.106%

    No Known Activations