© 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 EvalsExportsAPI 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. 30631
    Prev
    Next
    INDEX
    Explanations

    medical terms and references to health 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
    404
    +0.13
    0.6%
    626
    +0.11
    0.5%
    291
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.10
    314
    +0.11
    -0.01
    232
    +0.10
    0.10
    Negative Logits
     Slayer
    -0.91
     bisexual
    -0.84
     Spiral
    -0.84
     Saras
    -0.83
     Goth
    -0.77
     McCorm
    -0.75
     Gamb
    -0.75
     Mus
    -0.73
     Sparrow
    -0.73
     Loft
    -0.72
    POSITIVE LOGITS
    ename
    1.36
    eme
    1.34
    ey
    1.34
    eth
    1.33
    ec
    1.33
    eh
    1.32
    eg
    1.31
    e
    1.28
    ete
    1.26
    eb
    1.26
    Activations Density 2.022%

    No Known Activations