© 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 12288
    9. 8-RES_FS12288-JB
    11. 1651
    Prev
    Next
    INDEX
    Explanations

    terms related to sports strategies and technical aspects, specifically in baseball pitching and offensive play

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    373
    +0.17
    0.8%
    207
    +0.11
    0.5%
    716
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    207
    +0.17
    0.04
    716
    +0.11
    0.04
    362
    +0.11
    0.04
    Negative Logits
    hes
    -0.67
    erto
    -0.67
    Ore
    -0.67
    ogie
    -0.66
    ican
    -0.62
     TAMADRA
    -0.61
    cest
    -0.60
    Limited
    -0.59
    resa
    -0.59
    ortium
    -0.58
    POSITIVE LOGITS
     standpoint
    1.81
     vantage
    1.56
     perspective
    1.54
     perspectives
    1.29
     viewpoint
    1.27
     outset
    1.26
     angles
    1.12
     afar
    1.11
     angle
    1.10
     distance
    1.02
    Activations Density 0.255%

    No Known Activations