© 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. 8938
    Prev
    Next
    INDEX
    Explanations

    mentions of theatrical releases and their performance metrics

    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
    459
    +0.11
    0.5%
    240
    +0.10
    0.5%
    374
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.17
    455
    +0.10
    0.14
    679
    +0.10
    0.15
    Negative Logits
    +.
    -0.74
    !.
    -0.70
    .[
    -0.63
    $.
    -0.63
    CI
    -0.63
    .
    -0.61
    .<
    -0.60
    *.
    -0.59
    .(
    -0.59
     ILCS
    -0.56
    POSITIVE LOGITS
     consists
    1.40
     is
    1.38
     has
    1.36
     was
    1.31
     appears
    1.30
     seems
    1.30
     hasn
    1.29
     contains
    1.27
     isn
    1.27
     lasts
    1.26
    Activations Density 1.988%

    No Known Activations