© 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. 12401
    Prev
    Next
    INDEX
    Explanations

    relevant numbers and rankings

    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
    567
    +0.13
    0.6%
    333
    +0.09
    0.4%
    719
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.04
    567
    +0.09
    0.03
    636
    +0.09
    0.03
    Negative Logits
    uncture
    -0.71
     befriend
    -0.69
    Joined
    -0.68
    het
    -0.68
    mith
    -0.66
    gage
    -0.63
    Engineers
    -0.62
    mong
    -0.62
    mentation
    -0.61
    apesh
    -0.61
    POSITIVE LOGITS
     transcripts
    0.92
     information
    0.90
     redacted
    0.88
     transcript
    0.87
     teaser
    0.83
     excerpts
    0.83
     trove
    0.81
     footage
    0.79
     catalogue
    0.79
     downloadable
    0.78
    Activations Density 0.203%

    No Known Activations