© 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. 4328
    Prev
    Next
    INDEX
    Explanations

    sentences that pose questions or inquiries

    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
    33
    +0.11
    0.5%
    273
    +0.10
    0.5%
    224
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.11
    0.21
    679
    +0.10
    0.17
    440
    +0.10
    0.14
    Negative Logits
    atche
    -0.69
    ère
    -0.68
    ozyg
    -0.66
    åħ
    -0.66
    orse
    -0.66
    ofi
    -0.65
     incorpor
    -0.63
    adra
    -0.62
    abit
    -0.61
    pread
    -0.61
    POSITIVE LOGITS
     answers
    0.97
    Answer
    0.95
     answered
    0.95
     answering
    0.90
     Answer
    0.88
     depends
    0.84
     Answers
    0.84
     unanswered
    0.83
     determine
    0.78
     Questions
    0.75
    Activations Density 1.420%

    No Known Activations