© 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. 26366
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting cues that indicate user engagement or interaction

    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
    264
    +0.09
    0.4%
    317
    +0.09
    0.4%
    42
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.09
    0.20
    107
    +0.09
    0.18
    640
    +0.09
    0.15
    Negative Logits
    FIG
    -0.74
    Variable
    -0.72
    Marginal
    -0.71
    within
    -0.70
     Suddenly
    -0.69
    Suddenly
    -0.66
    Internal
    -0.65
    Second
    -0.65
    IQ
    -0.64
    1986
    -0.64
    POSITIVE LOGITS
     airs
    1.01
    Follow
    0.93
    malink
    0.93
    Thumbnail
    0.92
     Subscribe
    0.90
    Tags
    0.88
     HuffPost
    0.87
    Subscribe
    0.86
     subscribe
    0.84
     contributed
    0.83
    Activations Density 0.763%

    No Known Activations