© 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. 31706
    Prev
    Next
    INDEX
    Explanations

    references to content moderation policies and user behavior guidelines

    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
    +0.22
    1.0%
    484
    +0.11
    0.5%
    697
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.22
    -0.01
    211
    +0.11
    0.01
    583
    +0.11
    0.01
    Negative Logits
    aminer
    -0.74
    azon
    -0.74
    hov
    -0.65
    natureconservancy
    -0.65
    Enlarge
    -0.63
    anted
    -0.62
    elong
    -0.61
    illin
    -0.61
    edin
    -0.60
    aukee
    -0.58
    POSITIVE LOGITS
    Thank
    0.62
     heartbeat
    0.62
     thanked
    0.61
    Congratulations
    0.60
    guyen
    0.60
    leck
    0.58
    Else
    0.56
    ç
    0.56
    Quest
    0.56
    ĪĴ
    0.56
    Activations Density 0.087%

    No Known Activations