© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 7600
    Prev
    Next
    INDEX
    Explanations

    phrases related to the passing or prediction of time

    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
    540
    +0.15
    0.7%
    124
    +0.09
    0.4%
    101
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.15
    0.01
    439
    +0.09
    0.01
    242
    +0.09
    0.01
    Negative Logits
    pora
    -0.72
    ises
    -0.70
    osh
    -0.68
     resid
    -0.68
    izable
    -0.68
    iversity
    -0.66
     Columb
    -0.66
    ise
    -0.66
    olulu
    -0.64
    icably
    -0.63
    POSITIVE LOGITS
    phrase
    0.90
    smanship
    0.82
    through
    0.81
     Passed
    0.79
     passage
    0.75
    forward
    0.73
    notes
    0.73
     Passage
    0.72
     Amendments
    0.72
     passages
    0.72
    Activations Density 0.010%

    No Known Activations