© 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. 26200
    Prev
    Next
    INDEX
    Explanations

    terms related to behavior and behavioral patterns

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.10
    0.5%
    748
    +0.09
    0.4%
    136
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.10
    -0.00
    613
    +0.09
    0.01
    288
    +0.09
    0.03
    Negative Logits
     NCT
    -0.93
    eous
    -0.82
     Dug
    -0.72
    pei
    -0.68
    ITED
    -0.66
    istries
    -0.66
    ources
    -0.65
    ÏĤ
    -0.64
     YPG
    -0.62
     Tomb
    -0.62
    POSITIVE LOGITS
    aviour
    1.52
    avior
    1.47
    avi
    1.17
    av
    0.98
    aved
    0.92
    aving
    0.91
    avin
    0.91
    avia
    0.82
    ave
    0.78
    cffffcc
    0.78
    Activations Density 0.176%

    No Known Activations