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

    Neuronpedia

    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. 29306
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "trial" in various contexts

    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
    314
    +0.10
    0.5%
    183
    +0.10
    0.4%
    332
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.10
    0.02
    288
    +0.10
    0.02
    500
    +0.09
    0.02
    Negative Logits
    otle
    -0.79
     Boh
    -0.77
    afort
    -0.76
    amera
    -0.75
    uts
    -0.74
    olor
    -0.70
    licks
    -0.67
    achu
    -0.65
    ledged
    -0.65
    ippi
    -0.63
    POSITIVE LOGITS
    osterone
    0.99
    ists
    0.94
     balloons
    0.91
     balloon
    0.86
    eer
    0.81
    ist
    0.78
    ization
    0.77
    neys
    0.75
    ogue
    0.74
    icular
    0.73
    Activations Density 0.088%

    No Known Activations