© 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. 8861
    Prev
    Next
    INDEX
    Explanations

    references to the concept of calories or caloric values

    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
    421
    +0.15
    0.7%
    314
    +0.13
    0.6%
    299
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.15
    0.03
    588
    +0.13
    0.02
    367
    +0.11
    0.02
    Negative Logits
     Cherokee
    -0.65
    lihood
    -0.62
     Lans
    -0.60
     Liberty
    -0.59
     Kens
    -0.58
     Lovecraft
    -0.58
     nomine
    -0.57
     Generations
    -0.57
    english
    -0.57
     Colossus
    -0.55
    POSITIVE LOGITS
    culation
    1.25
    cium
    1.23
    culated
    1.20
    endar
    1.19
    endars
    1.16
    culus
    1.15
    ibr
    1.14
    iphate
    1.13
    orie
    1.10
    gary
    1.09
    Activations Density 0.040%

    No Known Activations