© 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. 10-RES_POST_32K-OAI
    11. 31477
    Prev
    Next
    INDEX
    Explanations

    actions related to political campaigns and electoral processes

    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
    373
    +0.14
    0.6%
    468
    +0.12
    0.6%
    705
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.14
    0.13
    665
    +0.12
    0.16
    241
    +0.11
    0.13
    Negative Logits
    nesota
    -0.62
     millenn
    -0.61
    ulin
    -0.59
    phies
    -0.59
    enery
    -0.58
    interstitial
    -0.58
    romy
    -0.57
    rities
    -0.56
    angular
    -0.55
    *)
    -0.55
    POSITIVE LOGITS
     anyway
    1.01
     sooner
    0.96
     lest
    0.95
     outright
    0.95
     uncond
    0.95
     nonetheless
    0.92
    Instead
    0.90
     anyways
    0.90
     boldly
    0.89
     cautiously
    0.88
    Activations Density 3.362%

    No Known Activations