© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5011
    Prev
    Next
    INDEX
    Explanations

    instances of numerical data or references to statistical figures

    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
    459
    +0.16
    0.7%
    583
    +0.09
    0.4%
    449
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.16
    0.10
    6
    +0.09
    0.07
    160
    +0.09
    0.07
    Negative Logits
    orporated
    -0.84
     DOS
    -0.64
     ambul
    -0.64
     append
    -0.63
     amput
    -0.62
    ``
    -0.62
     NRS
    -0.62
     Klux
    -0.61
     observation
    -0.59
    \">
    -0.58
    POSITIVE LOGITS
    farious
    0.74
    advertising
    0.71
     Catch
    0.68
    rawdownloadcloneembedreportprint
    0.66
    ilee
    0.65
     Buffer
    0.65
     Subtle
    0.64
    loe
    0.64
     Ingredients
    0.64
    advertisement
    0.63
    Activations Density 0.445%

    No Known Activations