© 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. 27115
    Prev
    Next
    INDEX
    Explanations

    occurrences of common articles, prepositions, and specific nouns

    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
    373
    +0.12
    0.5%
    380
    +0.12
    0.5%
    654
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    521
    +0.12
    0.00
    491
    +0.12
    0.01
    214
    +0.12
    0.00
    Negative Logits
     subp
    -0.79
    schild
    -0.77
    inka
    -0.72
    indal
    -0.71
    imov
    -0.66
    atoon
    -0.62
    veyard
    -0.62
     Stain
    -0.61
     hereafter
    -0.61
    obos
    -0.61
    POSITIVE LOGITS
    ertodd
    0.80
    ently
    0.70
    ername
    0.70
    Ask
    0.66
    animous
    0.66
    yp
    0.64
    Token
    0.63
    Did
    0.63
    olicited
    0.62
    Clean
    0.62
    Activations Density 0.028%

    No Known Activations