© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26546
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or identifiers related to events or organizations

    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
    343
    +0.12
    0.5%
    406
    +0.11
    0.5%
    757
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.12
    0.01
    304
    +0.11
    0.01
    33
    +0.09
    0.01
    Negative Logits
    berman
    -0.79
    oqu
    -0.74
    olson
    -0.73
    çīĪ
    -0.72
    psey
    -0.70
    psy
    -0.69
    footed
    -0.64
    acular
    -0.63
    ppings
    -0.62
    rael
    -0.60
    POSITIVE LOGITS
     Pis
    0.67
     Piece
    0.66
    Ĭ±
    0.63
     Nig
    0.62
    anooga
    0.61
    Cow
    0.61
     Minute
    0.60
     Mama
    0.59
    åī
    0.59
    Girls
    0.59
    Activations Density 0.029%

    No Known Activations