© 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. 8791
    Prev
    Next
    INDEX
    Explanations

    conjunctions, particularly "but" and variations indicating contrast or exception

    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
    12
    +0.11
    0.5%
    151
    +0.09
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.11
    0.01
    203
    +0.09
    0.01
    598
    +0.09
    0.01
    Negative Logits
     groom
    -0.65
    tsky
    -0.62
    =-=-=-=-=-=-=-=-
    -0.62
    iewicz
    -0.59
    lite
    -0.58
    oos
    -0.58
    BACK
    -0.57
     unrestricted
    -0.56
    stood
    -0.56
    tis
    -0.56
    POSITIVE LOGITS
    å¼
    0.73
    ãĥīãĥ©
    0.71
    ãĤ¨
    0.67
    é¾įå
    0.66
    é¾įåĸļ士
    0.62
    è»
    0.62
     DISTRICT
    0.62
    ãĤ¡
    0.61
    é£
    0.61
     è£ıç
    0.61
    Activations Density 0.065%

    No Known Activations