© 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. 31322
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their affiliations

    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
    316
    +0.13
    0.6%
    573
    +0.12
    0.5%
    506
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.01
    232
    +0.12
    0.02
    374
    +0.09
    -0.00
    Negative Logits
     glim
    -1.02
    krit
    -0.87
    sonian
    -0.80
     arrang
    -0.79
    ensibly
    -0.79
    eele
    -0.74
    anmar
    -0.74
    emis
    -0.72
     dunno
    -0.71
    vertisement
    -0.69
    POSITIVE LOGITS
     Latest
    1.02
     [
    0.78
     [[
    0.78
     Cosponsors
    0.77
     >>>
    0.76
    ]]
    0.72
     <<
    0.71
     AIDS
    0.70
     Sponsor
    0.68
     ``(
    0.66
    Activations Density 0.072%

    No Known Activations