© 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. 26221
    Prev
    Next
    INDEX
    Explanations

    references to individuals or identifiers in a digital/blockchain context

    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
    352
    +0.11
    0.5%
    597
    +0.10
    0.5%
    211
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.11
    0.01
    80
    +0.10
    0.00
    308
    +0.10
    0.02
    Negative Logits
     mattress
    -0.87
     Zot
    -0.86
     butter
    -0.82
    Lev
    -0.81
     ;;
    -0.81
     Zionist
    -0.81
     Playstation
    -0.80
    ãĥĨãĤ£
    -0.80
    TPPStreamerBot
    -0.79
    disk
    -0.77
    POSITIVE LOGITS
    Ang
    1.91
     Ang
    1.80
    ang
    1.79
    ANG
    1.61
    ng
    1.47
     ang
    1.45
     Ung
    1.43
     Lang
    1.42
     ANG
    1.40
    angs
    1.36
    Activations Density 5.135%

    No Known Activations