© 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. 26308
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and experiences of hurt or discomfort

    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
    259
    +0.13
    0.6%
    27
    +0.12
    0.5%
    762
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    676
    +0.13
    0.13
    213
    +0.12
    0.10
    139
    +0.11
    0.11
    Negative Logits
     Provision
    -0.78
     Profit
    -0.77
    olicy
    -0.74
    successfully
    -0.74
    SourceFile
    -0.73
     Tactics
    -0.72
     Vendor
    -0.71
     Funding
    -0.68
     Backup
    -0.68
     Achieve
    -0.68
    POSITIVE LOGITS
     saddened
    1.17
     haunted
    1.05
     bothers
    1.04
     bothered
    1.03
     dawn
    1.00
     reminded
    1.00
     pains
    0.98
     unn
    0.98
     startled
    0.96
     distur
    0.96
    Activations Density 0.930%

    No Known Activations