© 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. 32690
    Prev
    Next
    INDEX
    Explanations

    mentions of Alzheimer's and Parkinson's diseases

    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
    379
    +0.10
    0.5%
    279
    +0.10
    0.4%
    45
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.10
    0.06
    67
    +0.10
    0.06
    404
    +0.09
    0.05
    Negative Logits
     Zoro
    -0.87
     Hayden
    -0.82
    bian
    -0.79
     Piper
    -0.77
    DERR
    -0.75
    ubb
    -0.72
    ramid
    -0.72
    ãĥĺ
    -0.72
    bender
    -0.72
    onew
    -0.71
    POSITIVE LOGITS
     Alzheimer
    1.56
     dementia
    1.55
     dement
    1.20
     disease
    1.19
     Neurolog
    1.11
     Alz
    1.10
     Parkinson
    1.08
     Disease
    1.07
     ALS
    1.06
     plaque
    1.01
    Activations Density 1.424%

    No Known Activations