© 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. 7422
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographic locations, particularly ones ending in 'gan' or 'ville'

    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
    314
    +0.15
    0.7%
    339
    +0.12
    0.6%
    211
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.15
    0.02
    547
    +0.12
    0.02
    201
    +0.12
    0.02
    Negative Logits
    manship
    -0.71
    wcsstore
    -0.70
    eme
    -0.67
    shire
    -0.66
    Oracle
    -0.65
    icester
    -0.64
    ught
    -0.63
    BOOK
    -0.63
     Jinn
    -0.60
    book
    -0.59
    POSITIVE LOGITS
    sburgh
    0.95
    izations
    0.85
    atoes
    0.79
    izable
    0.77
    ous
    0.75
    olina
    0.74
    riages
    0.73
     externalToEVAOnly
    0.73
    gomery
    0.71
    atoon
    0.71
    Activations Density 0.079%

    No Known Activations