© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4662
    Prev
    Next
    INDEX
    Explanations

    questions, particularly those asking for clarification or information

    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
    373
    +0.14
    0.6%
    120
    +0.13
    0.6%
    605
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.14
    0.08
    285
    +0.13
    0.06
    166
    +0.10
    0.06
    Negative Logits
    virt
    -0.77
    ãĥ¼ãĤ¯
    -0.70
    ilon
    -0.69
    example
    -0.69
    norm
    -0.68
    grade
    -0.67
    ãĥ¼ãĥ«
    -0.66
    leg
    -0.66
    law
    -0.65
    armed
    -0.65
    POSITIVE LOGITS
     Lastly
    1.01
     THANK
    0.79
    Lastly
    0.76
     unanswered
    0.74
     Finally
    0.74
     answered
    0.74
     answers
    0.73
     Inqu
    0.71
     Thank
    0.71
     MORE
    0.70
    Activations Density 0.316%

    No Known Activations