© 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. 8947
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and variations of personal pronouns

    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
    489
    +0.14
    0.6%
    546
    +0.11
    0.5%
    192
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.17
    393
    +0.11
    0.11
    385
    +0.09
    0.10
    Negative Logits
     testimonies
    -0.85
     discussions
    -0.85
     implementations
    -0.83
     complaints
    -0.82
     signatures
    -0.81
     nods
    -0.80
     trials
    -0.80
     withdrawals
    -0.80
     decisions
    -0.79
     registrations
    -0.79
    POSITIVE LOGITS
    wrong
    0.97
     spouse
    0.85
    ãĥ¤
    0.81
     specified
    0.80
     oneself
    0.80
     wrong
    0.79
    someone
    0.79
    estamp
    0.76
    apeake
    0.74
    riber
    0.73
    Activations Density 0.895%

    No Known Activations