© 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. 27466
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and significant entities

    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
    308
    +0.12
    0.5%
    641
    +0.10
    0.4%
    175
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.12
    0.01
    308
    +0.10
    0.01
    314
    +0.10
    -0.01
    Negative Logits
    aukee
    -0.71
     compliment
    -0.64
    edly
    -0.63
    eret
    -0.62
     plague
    -0.61
    puter
    -0.61
     showc
    -0.59
     Sahara
    -0.58
    bara
    -0.58
    ende
    -0.58
    POSITIVE LOGITS
    é¾įåĸļ士
    1.39
    é¾įå
    1.27
    é¾į
    1.16
    ç¥ŀ
    1.11
    æĦ
    0.93
    士
    0.92
    å°Ĩ
    0.84
    é¾įå¥ij士
    0.84
    女
    0.82
    å¿
    0.81
    Activations Density 0.038%

    No Known Activations