© 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. 8-RES_POST_32K-OAI
    11. 7264
    Prev
    Next
    INDEX
    Explanations

    metadata in a structured data format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    373
    +0.12
    0.6%
    550
    +0.11
    0.5%
    453
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.12
    0.02
    692
    +0.11
    0.01
    541
    +0.10
    0.02
    Negative Logits
    reb
    -0.97
    gross
    -0.95
    cream
    -0.85
    vell
    -0.84
    susp
    -0.84
    carb
    -0.83
    cup
    -0.83
    adult
    -0.82
    offensive
    -0.82
    Rated
    -0.82
    POSITIVE LOGITS
     [];
    1.01
     []
    0.99
     "{
    0.95
     "\
    0.91
     {}
    0.90
     ""
    0.87
     {
    0.86
     "/
    0.85
     JSON
    0.81
     null
    0.81
    Activations Density 0.094%

    No Known Activations