© 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. 124
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and political analysis

    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
    282
    +0.11
    0.5%
    49
    +0.11
    0.5%
    370
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.11
    0.04
    49
    +0.11
    0.04
    718
    +0.10
    0.04
    Negative Logits
     enthusi
    -0.71
     Pathfinder
    -0.71
     IG
    -0.69
     Axis
    -0.68
     SEA
    -0.67
     Bundle
    -0.66
     Scroll
    -0.66
     pecul
    -0.66
     gears
    -0.65
     acron
    -0.65
    POSITIVE LOGITS
    tta
    0.93
    lis
    0.90
    nect
    0.90
    nt
    0.90
    lé
    0.90
    transfer
    0.90
    len
    0.89
    lear
    0.87
    lich
    0.87
    ucket
    0.87
    Activations Density 0.181%

    No Known Activations