© 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. 8748
    Prev
    Next
    INDEX
    Explanations

    actions related to entering and existing spaces or places

    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
    151
    +0.13
    0.6%
    341
    +0.10
    0.5%
    436
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.13
    0.08
    123
    +0.10
    0.10
    665
    +0.09
    0.10
    Negative Logits
     endorsements
    -0.68
     endors
    -0.64
     endorsement
    -0.62
     ebook
    -0.61
     Keynes
    -0.61
     therapist
    -0.61
     interoper
    -0.60
     NFL
    -0.60
     NHL
    -0.59
    FC
    -0.59
    POSITIVE LOGITS
     largeDownload
    0.85
     nearby
    0.73
    Haunted
    0.73
    ropri
    0.71
    ":[{"
    0.70
    é¾įåĸļ士
    0.69
    scl
    0.69
     Beware
    0.68
     cramped
    0.67
     upstairs
    0.65
    Activations Density 1.856%

    No Known Activations