© 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. 22939
    Prev
    Next
    INDEX
    Explanations

    verbs indicating movement or physical action

    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
    481
    +0.15
    0.7%
    342
    +0.12
    0.6%
    678
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.15
    0.06
    468
    +0.12
    0.05
    469
    +0.10
    0.04
    Negative Logits
     personalized
    -0.68
     specialization
    -0.67
     Savings
    -0.63
     guarantee
    -0.62
     economics
    -0.61
     promoter
    -0.61
     buyer
    -0.61
    Deal
    -0.60
     Prel
    -0.60
     affiliate
    -0.60
    POSITIVE LOGITS
     upright
    1.11
     sideways
    1.11
     awkwardly
    1.07
     crou
    1.03
     onto
    1.01
     downwards
    1.00
     horizontally
    0.97
     perpend
    0.97
     backwards
    0.95
     perpendicular
    0.93
    Activations Density 0.257%

    No Known Activations