© 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. 32765
    Prev
    Next
    INDEX
    Explanations

    phrases expressing agreement or acknowledgment

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    750
    +0.14
    0.6%
    544
    +0.10
    0.5%
    763
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.14
    0.06
    589
    +0.10
    0.05
    95
    +0.08
    0.05
    Negative Logits
    ĸļ
    -0.83
    arest
    -0.80
    ciplinary
    -0.75
    ivalent
    -0.73
    ridges
    -0.73
    İĭ
    -0.72
    Ń·
    -0.70
    icial
    -0.69
    emonic
    -0.68
    heimer
    -0.68
    POSITIVE LOGITS
     stuff
    0.95
     guy
    0.95
     shit
    0.86
     crap
    0.83
     because
    0.81
     rumor
    0.78
     idea
    0.76
     story
    0.75
     though
    0.74
     dude
    0.74
    Activations Density 0.400%

    No Known Activations