© 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. 8-RES_POST_32K-OAI
    11. 9073
    Prev
    Next
    INDEX
    Explanations

    references to a specific cycling team

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    89
    +0.12
    0.6%
    151
    +0.12
    0.6%
    218
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.02
    284
    +0.12
    0.02
    316
    +0.11
    0.02
    Negative Logits
    KE
    -0.71
    idence
    -0.67
    ARY
    -0.65
    UTION
    -0.64
    OUGH
    -0.64
     "$:/
    -0.64
    utes
    -0.63
     spiral
    -0.62
    asion
    -0.62
    KS
    -0.61
    POSITIVE LOGITS
    ophon
    1.08
    lest
    0.96
    ophone
    0.90
    leness
    0.89
    ean
    0.83
    onial
    0.81
    bones
    0.79
    ãĤ¼ãĤ¦ãĤ¹
    0.75
    ecast
    0.73
    mented
    0.72
    Activations Density 0.077%

    No Known Activations