© 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. 8-RES_POST_32K-OAI
    11. 4225
    Prev
    Next
    INDEX
    Explanations

    phrases that express inquiries or questions

    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
    519
    +0.12
    0.5%
    541
    +0.11
    0.5%
    196
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.12
    0.05
    718
    +0.11
    0.07
    282
    +0.11
    0.06
    Negative Logits
    ool
    -0.72
    ufact
    -0.71
     Deluxe
    -0.68
     Slater
    -0.66
    ilon
    -0.63
    photos
    -0.63
     miraculous
    -0.62
    ellow
    -0.62
    robe
    -0.61
    natureconservancy
    -0.61
    POSITIVE LOGITS
     answered
    1.41
    answer
    1.37
    answered
    1.33
     unanswered
    1.28
    Answer
    1.23
     answering
    1.17
     answers
    1.15
     answ
    1.14
     Answers
    1.11
     asked
    1.04
    Activations Density 1.696%

    No Known Activations