© 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. 28726
    Prev
    Next
    INDEX
    Explanations

    references to the reader or audience in a directive or engaging manner

    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
    548
    +0.11
    0.5%
    653
    +0.11
    0.5%
    497
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.01
    49
    +0.11
    0.03
    211
    +0.11
    0.02
    Negative Logits
    yss
    -0.91
    oday
    -0.74
    idae
    -0.70
    terness
    -0.69
    wana
    -0.68
    idon
    -0.67
    wings
    -0.67
    escription
    -0.66
     Franç
    -0.66
    gins
    -0.65
    POSITIVE LOGITS
    're
    0.73
    'll
    0.72
    've
    0.71
     scope
    0.65
    EStreamFrame
    0.65
    é»Ĵ
    0.63
    'd
    0.61
     pulse
    0.51
     Probably
    0.51
     ought
    0.51
    Activations Density 0.067%

    No Known Activations