© 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. 26932
    Prev
    Next
    INDEX
    Explanations

    elements of computer code or programming syntax

    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
    22
    +0.12
    0.5%
    38
    +0.11
    0.5%
    303
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.09
    678
    +0.11
    0.04
    738
    +0.10
    0.03
    Negative Logits
     coaster
    -0.90
    idepress
    -0.81
     Cave
    -0.81
     Robotics
    -0.80
    onic
    -0.80
     chees
    -0.80
     ObamaCare
    -0.78
    thodox
    -0.78
    anooga
    -0.76
     Franken
    -0.75
    POSITIVE LOGITS
     var
    2.19
    var
    1.94
    Var
    1.66
     Var
    1.66
     func
    1.03
     variable
    1.00
    func
    0.93
    vari
    0.90
     Terry
    0.89
    variable
    0.89
    Activations Density 1.321%

    No Known Activations