© 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. 26578
    Prev
    Next
    INDEX
    Explanations

    terms related to keyboards and typing, including layouts and shortcuts

    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
    288
    +0.12
    0.5%
    435
    +0.11
    0.5%
    417
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.03
    435
    +0.11
    0.02
    326
    +0.11
    0.03
    Negative Logits
    hig
    -0.78
     Pharmaceutical
    -0.75
     Volunte
    -0.75
     Scient
    -0.74
    ns
    -0.73
    gio
    -0.71
     Gaul
    -0.67
    tro
    -0.66
     Directorate
    -0.65
     Gleaming
    -0.64
    POSITIVE LOGITS
     shortcuts
    1.19
     shortcut
    1.07
     layouts
    0.92
     layout
    0.87
    ists
    0.82
    caps
    0.79
    cap
    0.77
    acters
    0.75
    ist
    0.74
    oat
    0.74
    Activations Density 0.136%

    No Known Activations