© 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. 26320
    Prev
    Next
    INDEX
    Explanations

    references to service-related contexts and regulations

    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
    179
    +0.13
    0.6%
    248
    +0.12
    0.5%
    58
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    248
    +0.13
    0.06
    179
    +0.12
    0.04
    679
    +0.10
    0.12
    Negative Logits
     Canaver
    -0.91
     bald
    -0.85
     hemp
    -0.82
     Bigfoot
    -0.81
     Mew
    -0.81
     Hemp
    -0.76
     genetically
    -0.76
     Barbie
    -0.75
     Colomb
    -0.75
     Zhang
    -0.75
    POSITIVE LOGITS
    Service
    2.37
     service
    2.36
    service
    2.33
     Service
    2.27
     SERVICE
    2.14
     services
    1.95
    services
    1.87
    serv
    1.81
    Services
    1.78
     Serv
    1.77
    Activations Density 3.650%

    No Known Activations