© 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. 29140
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the presence of an audience or gathering

    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
    168
    +0.11
    0.5%
    327
    +0.09
    0.4%
    228
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.11
    0.03
    327
    +0.09
    0.03
    362
    +0.09
    0.04
    Negative Logits
    berman
    -0.78
    leep
    -0.73
    pring
    -0.69
    isure
    -0.65
    hower
    -0.64
    ierra
    -0.64
    terday
    -0.63
    unker
    -0.61
    onics
    -0.61
    ravel
    -0.61
    POSITIVE LOGITS
     cameras
    1.19
     camera
    1.04
     mirror
    0.98
     audiences
    0.93
     microphones
    0.89
     cheering
    0.89
     crowds
    0.89
     mirrors
    0.86
     roaring
    0.85
     eyes
    0.82
    Activations Density 0.475%

    No Known Activations