© 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. 10-RES_POST_32K-OAI
    11. 26585
    Prev
    Next
    INDEX
    Explanations

    instances of agreement or consensus in contexts involving cooperation or collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    679
    +0.10
    0.5%
    665
    +0.10
    0.4%
    70
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.10
    0.03
    70
    +0.10
    0.03
    665
    +0.09
    0.03
    Negative Logits
    asus
    -0.78
    vantage
    -0.77
    osaurs
    -0.72
    govtrack
    -0.72
    crow
    -0.71
     Tycoon
    -0.67
     Takeru
    -0.65
    jiang
    -0.65
    ¥ŀ
    -0.64
    ordinary
    -0.64
    POSITIVE LOGITS
     unanimously
    1.01
     upon
    0.85
     beforehand
    0.77
     voluntarily
    0.77
     terms
    0.76
     collectively
    0.73
    upon
    0.72
    umm
    0.70
     stip
    0.69
     indemn
    0.68
    Activations Density 0.085%

    No Known Activations