© 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. 6255
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "quest" and its variations to identify themes of exploration or seeking

    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
    321
    +0.10
    0.4%
    651
    +0.10
    0.4%
    681
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.10
    0.01
    641
    +0.10
    0.01
    575
    +0.10
    0.01
    Negative Logits
     Unic
    -0.60
    creen
    -0.58
     sexes
    -0.58
    olor
    -0.57
     Bayer
    -0.57
    lihood
    -0.57
     guiName
    -0.56
    bestos
    -0.56
     Slater
    -0.56
     retire
    -0.56
    POSITIVE LOGITS
    ioned
    1.27
    naire
    1.08
    naires
    0.99
    icular
    0.93
    love
    0.93
    ogue
    0.87
    finding
    0.86
    finder
    0.83
    line
    0.83
    ing
    0.82
    Activations Density 0.042%

    No Known Activations