© 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. 30660
    Prev
    Next
    INDEX
    Explanations

    actions or intentions to influence or intervene in a political context

    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
    741
    +0.11
    0.5%
    718
    +0.10
    0.5%
    531
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.14
    139
    +0.10
    0.13
    665
    +0.10
    0.13
    Negative Logits
    plugins
    -0.79
    comments
    -0.78
     Printed
    -0.71
    prints
    -0.70
    *)
    -0.69
    nesota
    -0.66
     elig
    -0.65
    ebook
    -0.64
    atin
    -0.63
    payment
    -0.62
    POSITIVE LOGITS
     compel
    1.06
     halt
    1.03
     topple
    0.99
     eradicate
    0.94
     restore
    0.93
     retake
    0.91
     crush
    0.91
     overthrow
    0.91
     undo
    0.90
     stop
    0.89
    Activations Density 0.660%

    No Known Activations