© 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 EvalsExportsinterp-engineNEWAPI 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. 32304
    Prev
    Next
    INDEX
    Explanations

    acronyms and keywords related to sports and technology

    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
    506
    +0.12
    0.6%
    650
    +0.11
    0.5%
    81
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.12
    0.06
    326
    +0.11
    0.06
    406
    +0.09
    0.04
    Negative Logits
    endez
    -0.88
    awaru
    -0.85
    ij士
    -0.83
    rette
    -0.76
    alty
    -0.76
    atem
    -0.74
    udeb
    -0.74
    chenko
    -0.72
    atin
    -0.71
    amus
    -0.71
    POSITIVE LOGITS
    BRE
    0.89
    STAR
    0.89
    W
    0.78
    word
    0.76
    WORK
    0.74
    WARE
    0.74
    VIEW
    0.74
    BALL
    0.73
    é¾įåĸļ士
    0.73
    PLAY
    0.72
    Activations Density 0.378%

    No Known Activations