© 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. 27346
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating relationships or connections

    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
    31
    +0.11
    0.5%
    588
    +0.11
    0.5%
    711
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    731
    +0.11
    0.03
    327
    +0.11
    0.06
    584
    +0.10
    0.07
    Negative Logits
    HT
    -0.81
    mith
    -0.67
    asin
    -0.67
    nikov
    -0.67
    ãĥĨãĤ£
    -0.66
    panic
    -0.66
    hey
    -0.62
    ãĤ¿
    -0.61
    BSD
    -0.61
    zinski
    -0.61
    POSITIVE LOGITS
     contrasts
    0.75
     parcel
    0.74
     contradiction
    0.73
     error
    0.72
     appellate
    0.72
     contrast
    0.69
     circumstance
    0.65
     apprentices
    0.65
     gown
    0.64
     conditioning
    0.62
    Activations Density 0.981%

    No Known Activations