© 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. 27275
    Prev
    Next
    INDEX
    Explanations

    function calls and parameters in code snippets

    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
    160
    +0.12
    0.5%
    314
    +0.10
    0.4%
    721
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.12
    0.06
    314
    +0.10
    0.00
    326
    +0.10
    0.04
    Negative Logits
     sq
    -0.79
     citiz
    -0.77
     (>
    -0.75
     vowel
    -0.72
     gobl
    -0.72
     coerc
    -0.72
     glim
    -0.71
     fraction
    -0.71
     (~
    -0.70
     photon
    -0.70
    POSITIVE LOGITS
    TAG
    1.13
    context
    1.02
    Context
    0.99
    Application
    0.94
    Http
    0.93
    Bridge
    0.92
    Camera
    0.92
    connection
    0.91
    this
    0.90
    params
    0.90
    Activations Density 0.300%

    No Known Activations