© 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. 30847
    Prev
    Next
    INDEX
    Explanations

    terms related to updates and features in a software or gaming context

    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
    94
    +0.13
    0.6%
    597
    +0.10
    0.5%
    307
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.13
    0.07
    723
    +0.10
    0.04
    326
    +0.10
    0.09
    Negative Logits
     Suppose
    -0.71
    omsky
    -0.71
    wikipedia
    -0.65
    cius
    -0.63
     Howell
    -0.62
    uyomi
    -0.62
    agine
    -0.62
    cart
    -0.61
     hegemony
    -0.60
     Draper
    -0.60
    POSITIVE LOGITS
     fixes
    1.28
     bug
    1.20
     optimizations
    1.13
     polish
    1.09
     stability
    1.07
    fixes
    1.06
     improvements
    1.05
     Fixes
    1.02
     minor
    1.00
     enhancements
    0.98
    Activations Density 1.434%

    No Known Activations