© 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. 26204
    Prev
    Next
    INDEX
    Explanations

    words relating to guilt or blame

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    390
    +0.11
    0.5%
    497
    +0.11
    0.5%
    275
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    -0.00
    232
    +0.11
    0.04
    659
    +0.10
    0.03
    Negative Logits
     Rivals
    -0.66
     correlate
    -0.61
     correlates
    -0.61
    00000
    -0.61
    audi
    -0.58
     Collider
    -0.57
     divide
    -0.57
     periphery
    -0.56
     neighbours
    -0.56
    8000
    -0.55
    POSITIVE LOGITS
    ably
    0.95
    ÃŃn
    0.89
    ptions
    0.87
    inka
    0.81
    pta
    0.78
    itions
    0.73
    irs
    0.73
    erella
    0.71
    cin
    0.69
    reau
    0.68
    Activations Density 0.354%

    No Known Activations