© 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. 31357
    Prev
    Next
    INDEX
    Explanations

    punctuation and mathematical symbols in a programming 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
    393
    +0.12
    0.5%
    251
    +0.09
    0.4%
    493
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.12
    0.08
    326
    +0.09
    0.06
    107
    +0.09
    0.06
    Negative Logits
     »
    -0.66
    soever
    -0.64
     Emmy
    -0.60
     "âĢ¦
    -0.60
     amen
    -0.59
     Artificial
    -0.59
     metaphors
    -0.58
    ãĢIJ
    -0.58
    .—
    -0.58
     Azerbai
    -0.56
    POSITIVE LOGITS
    parse
    0.91
    get
    0.85
    radius
    0.84
    current
    0.83
    max
    0.82
    utils
    0.81
    eq
    0.81
    init
    0.80
    error
    0.78
    width
    0.78
    Activations Density 0.254%

    No Known Activations