© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 9562
    Prev
    Next
    INDEX
    Explanations

    references to a person named "Danny" that seems to be a recurring character or topic in various contexts.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    515
    +0.10
    0.4%
    200
    +0.10
    0.4%
    549
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    515
    +0.10
    0.01
    659
    +0.10
    0.01
    134
    +0.09
    0.01
    Negative Logits
    sburgh
    -1.19
    sites
    -0.89
    atcher
    -0.80
    rontal
    -0.77
    erer
    -0.75
    exec
    -0.73
    cies
    -0.71
    nir
    -0.70
    INS
    -0.70
    fitting
    -0.69
    POSITIVE LOGITS
     Amend
    0.86
     Glover
    0.81
     DeV
    0.77
     Boyle
    0.76
    bars
    0.76
    Hamilton
    0.75
     Meyer
    0.74
     Masters
    0.73
     Drink
    0.70
     Webb
    0.69
    Activations Density 0.017%

    No Known Activations