© 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. 29229
    Prev
    Next
    INDEX
    Explanations

    elements related to data formatting or structured lists

    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
    731
    +0.10
    0.5%
    424
    +0.10
    0.5%
    713
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    731
    +0.10
    0.03
    512
    +0.10
    0.07
    514
    +0.10
    0.05
    Negative Logits
    yss
    -1.04
     Ez
    -0.83
     Yus
    -0.82
    Jenn
    -0.81
     Galile
    -0.80
     Jennings
    -0.78
     Sie
    -0.77
     Serge
    -0.77
    ief
    -0.75
    Ly
    -0.74
    POSITIVE LOGITS
    74
    1.39
    75
    1.34
     74
    1.33
    73
    1.25
     73
    1.23
     75
    1.21
    76
    1.20
    72
    1.17
     72
    1.08
    754
    1.07
    Activations Density 1.526%

    No Known Activations