© 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. 9110
    Prev
    Next
    INDEX
    Explanations

    references to smoking and its effects or related behaviors

    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
    373
    +0.11
    0.5%
    203
    +0.10
    0.5%
    35
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.11
    0.02
    698
    +0.10
    0.02
    726
    +0.10
    0.02
    Negative Logits
    ousse
    -0.69
     Defenders
    -0.68
     Merge
    -0.64
    ngth
    -0.62
     Awards
    -0.61
     awards
    -0.61
     Vector
    -0.61
    ensional
    -0.60
    herty
    -0.60
     GOODMAN
    -0.59
    POSITIVE LOGITS
     cessation
    1.20
     cigarettes
    1.13
     smoking
    1.00
     cig
    0.96
     smoked
    0.94
    creen
    0.93
    arette
    0.92
     smoker
    0.92
     smoke
    0.90
     cigarette
    0.87
    Activations Density 0.060%

    No Known Activations