© 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. 26282
    Prev
    Next
    INDEX
    Explanations

    keywords related to psychological measurements and conditions in a clinical context

    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
    252
    +0.11
    0.5%
    317
    +0.11
    0.5%
    509
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.11
    0.09
    720
    +0.11
    0.10
    73
    +0.09
    0.08
    Negative Logits
    wered
    -0.75
    doesn
    -0.72
     Nope
    -0.71
     hated
    -0.70
     whis
    -0.67
    terday
    -0.66
     Won
    -0.66
     Steal
    -0.66
     Plenty
    -0.66
     booze
    -0.65
    POSITIVE LOGITS
    Figure
    1.03
     suggesting
    1.03
     âĪ¼
    1.01
     consistent
    1.00
     Supplementary
    0.98
     indicating
    0.94
     respectively
    0.88
     characterized
    0.88
     demonstrating
    0.87
    Supplement
    0.84
    Activations Density 0.582%

    No Known Activations