© 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. 10-RES_POST_32K-OAI
    11. 32312
    Prev
    Next
    INDEX
    Explanations

    references to volcanic activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    314
    +0.11
    0.5%
    682
    +0.10
    0.5%
    211
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.11
    0.02
    257
    +0.10
    0.02
    580
    +0.10
    0.02
    Negative Logits
     Sunder
    -0.73
     Synd
    -0.70
     Sphere
    -0.67
     Elven
    -0.64
     Languages
    -0.64
     LCS
    -0.63
     Ninth
    -0.63
     synd
    -0.63
    Ranked
    -0.61
     Syri
    -0.59
    POSITIVE LOGITS
    atile
    1.54
    untary
    1.50
    untarily
    1.38
    atility
    1.38
    unte
    1.36
    umes
    1.30
    cano
    1.29
    leys
    1.12
    upt
    1.09
    itional
    1.06
    Activations Density 0.068%

    No Known Activations