© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22184
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports performance and statistics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    745
    +0.11
    0.5%
    281
    +0.10
    0.5%
    533
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    281
    +0.11
    0.05
    533
    +0.10
    0.05
    668
    +0.10
    0.04
    Negative Logits
     unemploy
    -0.89
    enegger
    -0.82
    quartered
    -0.80
     Canaver
    -0.78
     PhD
    -0.74
    reprene
    -0.73
     Volunte
    -0.73
     IEEE
    -0.72
     Profession
    -0.72
    Bloomberg
    -0.71
    POSITIVE LOGITS
     offensively
    1.22
     defensively
    1.19
     halftime
    1.13
     scrimmage
    1.04
     turnovers
    1.02
     midfield
    1.00
     scoreboard
    0.93
     blitz
    0.90
     firepower
    0.89
     dominating
    0.89
    Activations Density 0.451%

    No Known Activations