© 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. 8756
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue or quotations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    563
    +0.11
    0.5%
    373
    +0.10
    0.5%
    666
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.11
    0.11
    314
    +0.10
    0.02
    160
    +0.10
    0.10
    Negative Logits
     confir
    -0.67
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
     TMZ
    -0.63
     LCS
    -0.61
     Harmony
    -0.61
    OTUS
    -0.60
     Ceres
    -0.57
     minus
    -0.56
     Unicorn
    -0.56
     Huff
    -0.55
    POSITIVE LOGITS
     "âĢ¦
    0.94
     "...
    0.87
    ³³³³³³³³
    0.82
     '[
    0.80
    "âĢ¦
    0.78
     [âĢ¦]
    0.76
     '
    0.74
    advertising
    0.71
    milo
    0.71
    "...
    0.70
    Activations Density 0.718%

    No Known Activations