© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27457
    Prev
    Next
    INDEX
    Explanations

    phrases related to requests for assistance or action

    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
    591
    +0.11
    0.5%
    129
    +0.11
    0.5%
    12
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.11
    0.07
    762
    +0.11
    0.07
    212
    +0.10
    0.03
    Negative Logits
    Newsletter
    -0.85
    iven
    -0.66
     STA
    -0.65
     engagements
    -0.62
    æĪ¦
    -0.60
    Supplement
    -0.60
     commencement
    -0.59
     Supplemental
    -0.58
    Continue
    -0.58
    cheon
    -0.57
    POSITIVE LOGITS
    else
    0.81
    who
    0.80
     whom
    0.75
     accuse
    0.73
    achy
    0.70
     seriously
    0.69
    kn
    0.67
    watch
    0.67
     wiser
    0.67
     argue
    0.67
    Activations Density 0.770%

    No Known Activations