© 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. 8-RES_POST_32K-OAI
    11. 4860
    Prev
    Next
    INDEX
    Explanations

    words related to actions and categorizations

    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
    407
    +0.12
    0.6%
    102
    +0.10
    0.5%
    26
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.12
    0.00
    373
    +0.10
    -0.01
    26
    +0.09
    0.01
    Negative Logits
     awa
    -0.97
    pora
    -0.81
     simultane
    -0.74
     ende
    -0.72
     mosqu
    -0.72
    stic
    -0.69
     unborn
    -0.67
     streng
    -0.67
     Niet
    -0.65
    urated
    -0.63
    POSITIVE LOGITS
     Consortium
    0.80
     Hera
    0.78
     Karn
    0.73
     Clair
    0.67
     Samurai
    0.66
    Recipe
    0.63
    éŃĶ
    0.62
    Shot
    0.62
    ItemImage
    0.62
    ULT
    0.61
    Activations Density 0.028%

    No Known Activations