© 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. 12986
    Prev
    Next
    INDEX
    Explanations

    the names of locations

    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
    760
    +0.09
    0.4%
    341
    +0.09
    0.4%
    245
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.09
    0.03
    659
    +0.09
    0.03
    5
    +0.09
    0.02
    Negative Logits
    éĸ
    -0.77
     contempor
    -0.72
     Liter
    -0.72
     Mahjong
    -0.71
     MON
    -0.71
     undersc
    -0.67
     hook
    -0.67
     college
    -0.66
     dial
    -0.66
     Foot
    -0.66
    POSITIVE LOGITS
    os
    1.76
    us
    1.45
    osa
    1.41
    oses
    1.15
    OS
    1.14
    osaurs
    1.12
    as
    1.10
    osity
    1.08
    nos
    1.07
    osite
    1.06
    Activations Density 0.057%

    No Known Activations