© 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. 30884
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and function definitions

    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
    233
    +0.13
    0.6%
    181
    +0.10
    0.5%
    246
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.16
    137
    +0.10
    0.00
    393
    +0.10
    0.15
    Negative Logits
    ATH
    -0.87
    Nin
    -0.83
     Tolkien
    -0.80
    Course
    -0.74
     Lod
    -0.74
     Alban
    -0.74
    lasses
    -0.73
    olkien
    -0.73
     Vil
    -0.73
    Las
    -0.72
    POSITIVE LOGITS
    press
    1.78
     presses
    1.67
     PRESS
    1.66
     press
    1.66
     Press
    1.65
    Push
    1.63
     Push
    1.60
    PRESS
    1.56
     pressing
    1.51
     push
    1.50
    Activations Density 4.470%

    No Known Activations