© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30356
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically semicolons

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.16
    0.7%
    378
    +0.12
    0.5%
    23
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.02
    284
    +0.12
    0.01
    678
    +0.11
    0.01
    Negative Logits
    anmar
    -0.64
    idated
    -0.64
    idation
    -0.62
    vision
    -0.58
     guiActiveUnfocused
    -0.58
     conscientious
    -0.57
    iggurat
    -0.57
     mindfulness
    -0.56
     councils
    -0.56
     Kira
    -0.55
    POSITIVE LOGITS
    ;;;;;;;;
    1.23
    ;;
    1.07
    ;;;;;;;;;;;;
    0.98
    ::::::::
    0.98
    -)
    0.88
    ================================================================
    0.83
    alias
    0.82
    --------------------------------------------------------
    0.80
    ospace
    0.79
    then
    0.78
    Activations Density 0.099%

    No Known Activations