© 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. 8-RES_POST_32K-OAI
    11. 8989
    Prev
    Next
    INDEX
    Explanations

    terms related to sensitivity and regeneration in a medical context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    68
    +0.12
    0.6%
    373
    +0.11
    0.5%
    488
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.12
    0.11
    426
    +0.11
    0.09
    23
    +0.10
    0.10
    Negative Logits
     Worker
    -0.72
     Maker
    -0.70
    jack
    -0.65
     FO
    -0.64
     Zimbabwe
    -0.63
     Takeru
    -0.63
     MO
    -0.63
     Gamb
    -0.62
     Kenyan
    -0.62
     Order
    -0.61
    POSITIVE LOGITS
    itivity
    1.29
    itive
    1.10
    orship
    1.00
    ors
    0.99
    ation
    0.99
    ational
    0.94
    itives
    0.90
    edIn
    0.88
    ĸļ
    0.88
    mble
    0.87
    Activations Density 0.482%

    No Known Activations