© 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. 17207
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs related to aesthetics and history, as well as words related to financial or economic terms

    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
    151
    +0.14
    0.6%
    97
    +0.11
    0.5%
    525
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.14
    0.05
    97
    +0.11
    0.03
    103
    +0.10
    0.04
    Negative Logits
     Klu
    -0.74
     Chiefs
    -0.73
    ger
    -0.71
     Cities
    -0.71
     Meteor
    -0.70
    ials
    -0.69
     Seasons
    -0.69
     Commissioners
    -0.68
     Cause
    -0.67
     Vikings
    -0.65
    POSITIVE LOGITS
     speaking
    0.96
     challenged
    0.94
     minded
    0.90
     inclined
    0.87
    significant
    0.86
     indistinguishable
    0.84
    responsible
    0.83
     detonated
    0.81
     disadvantaged
    0.81
     oriented
    0.80
    Activations Density 0.073%

    No Known Activations