© 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 EvalsExportsinterp-engineNEWAPI 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. 22412
    Prev
    Next
    INDEX
    Explanations

    terms related to causation and influence

    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
    240
    +0.10
    0.4%
    195
    +0.09
    0.4%
    166
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    541
    +0.10
    0.04
    665
    +0.09
    0.04
    240
    +0.09
    0.03
    Negative Logits
    IFT
    -0.70
    urai
    -0.68
    oos
    -0.64
    ç«
    -0.62
     Guinness
    -0.61
    owe
    -0.58
    akings
    -0.58
    atari
    -0.57
     Haku
    -0.57
    rooms
    -0.56
    POSITIVE LOGITS
     by
    1.24
    by
    1.03
     BY
    0.93
     solely
    0.92
    By
    0.91
     principally
    0.88
     chiefly
    0.88
     By
    0.84
    BY
    0.80
     primarily
    0.78
    Activations Density 0.124%

    No Known Activations