© 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. 26208
    Prev
    Next
    INDEX
    Explanations

    mentions of subscription-related elements and promotional offers

    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
    756
    +0.12
    0.6%
    755
    +0.12
    0.6%
    39
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.01
    755
    +0.12
    0.01
    211
    +0.11
    0.01
    Negative Logits
     unprotected
    -0.65
     unrest
    -0.64
    atism
    -0.63
    \/\/
    -0.60
    AIDS
    -0.59
    rest
    -0.58
    ngth
    -0.57
     dissatisfaction
    -0.57
    obyl
    -0.56
     unpop
    -0.56
    POSITIVE LOGITS
     Centauri
    0.69
    odon
    0.66
    merce
    0.61
     Bottom
    0.60
    ines
    0.60
    reads
    0.56
     subtitle
    0.56
    ({
    0.56
    VERTISEMENT
    0.55
    Trend
    0.55
    Activations Density 0.069%

    No Known Activations