Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 21523
    Prev
    Next
    INDEX
    Explanations

    dates and events related to historical ships and disasters

    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
    640
    +0.30
    1.4%
    160
    +0.17
    0.8%
    442
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.30
    0.08
    160
    +0.17
    0.08
    442
    +0.13
    0.07
    Negative Logits
     crunch
    -0.78
     casc
    -0.78
     yours
    -0.73
     compr
    -0.72
     freel
    -0.72
     hers
    -0.71
     lifes
    -0.70
     ones
    -0.70
     prosec
    -0.70
     damned
    -0.70
    POSITIVE LOGITS
    References
    1.75
    Trivia
    1.67
    Appearances
    1.66
    Notable
    1.64
    Contents
    1.61
    History
    1.59
    Gallery
    1.51
    Other
    1.44
    Notes
    1.44
    See
    1.43
    Activations Density 0.193%

    No Known Activations