© 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. 31215
    Prev
    Next
    INDEX
    Explanations

    words related to mental health and psychiatric conditions

    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
    228
    +0.10
    0.5%
    382
    +0.10
    0.4%
    493
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    449
    +0.10
    0.06
    156
    +0.10
    0.06
    239
    +0.09
    0.07
    Negative Logits
     irrig
    -1.06
    awei
    -0.85
    Vel
    -0.84
     Herrera
    -0.84
     Pork
    -0.84
     vel
    -0.83
    artifacts
    -0.82
     Vel
    -0.80
     gloves
    -0.78
     irrigation
    -0.78
    POSITIVE LOGITS
     psychiatric
    1.95
     psychiatrists
    1.94
     psychiatry
    1.89
     DSM
    1.79
     Psychiatric
    1.78
     Psychiatry
    1.78
     Psychiat
    1.77
     psychiatrist
    1.75
     psychosis
    1.75
     schizophrenia
    1.72
    Activations Density 5.504%

    No Known Activations