© 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. 32633
    Prev
    Next
    INDEX
    Explanations

    terms related to psychiatric disorders and their symptoms

    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
    559
    +0.12
    0.5%
    545
    +0.10
    0.5%
    225
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    559
    +0.12
    0.03
    616
    +0.10
    0.05
    493
    +0.09
    0.04
    Negative Logits
     Canaver
    -0.85
     Jenner
    -0.77
     microphones
    -0.75
    liest
    -0.70
    Origin
    -0.70
    ufact
    -0.69
     unborn
    -0.69
    ãĤ¨ãĥ«
    -0.67
     healed
    -0.67
     Miko
    -0.67
    POSITIVE LOGITS
     impuls
    1.25
     binge
    1.00
     obsessive
    0.99
     anxiety
    0.97
     compuls
    0.97
     anxious
    0.90
     bipolar
    0.87
     suicidal
    0.87
     Anxiety
    0.86
    hyper
    0.86
    Activations Density 1.092%

    No Known Activations