© 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. 9113
    Prev
    Next
    INDEX
    Explanations

    references to time periods and the emotional context associated with them

    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
    377
    +0.12
    0.5%
    3
    +0.10
    0.4%
    150
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.12
    0.07
    377
    +0.10
    0.06
    383
    +0.09
    0.04
    Negative Logits
     violates
    -0.62
     implements
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.60
    Increases
    -0.60
    resistant
    -0.60
     Incre
    -0.59
    isite
    -0.59
    icago
    -0.59
    icably
    -0.58
     guiActiveUn
    -0.58
    POSITIVE LOGITS
    ————————
    0.71
    nings
    0.71
     affair
    0.70
     indeed
    0.70
    ————
    0.69
     ahead
    0.65
     outing
    0.64
    tty
    0.63
     imaginable
    0.63
     Khe
    0.62
    Activations Density 0.484%

    No Known Activations