© 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. 11032
    Prev
    Next
    INDEX
    Explanations

    numeric ranges, such as rankings or measurements, and financial values

    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
    314
    +0.10
    0.5%
    102
    +0.10
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.10
    0.04
    616
    +0.10
    0.03
    102
    +0.10
    0.03
    Negative Logits
     Bullets
    -0.73
     Hicks
    -0.69
     Indigo
    -0.69
     Cox
    -0.67
     Borders
    -0.67
     Daylight
    -0.66
     Kits
    -0.65
     Boat
    -0.65
     dialog
    -0.63
     lull
    -0.63
    POSITIVE LOGITS
    ever
    1.40
    ranked
    1.33
    performing
    1.21
    selling
    1.18
    ranking
    1.17
    known
    1.16
    funded
    1.10
    favorite
    1.10
    worst
    1.10
    connected
    1.07
    Activations Density 0.054%

    No Known Activations