© 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. 24398
    Prev
    Next
    INDEX
    Explanations

    action-related terms and verbs, particularly those associated with "act" and its variations

    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
    496
    +0.13
    0.6%
    642
    +0.13
    0.6%
    208
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.13
    0.02
    208
    +0.13
    0.01
    441
    +0.12
    0.01
    Negative Logits
    PDATE
    -0.76
    conservancy
    -0.70
    Ń·
    -0.69
     proble
    -0.66
     inund
    -0.64
    ĨĴ
    -0.63
     administ
    -0.63
     pigeon
    -0.62
    £ı
    -0.61
    ceptor
    -0.60
    POSITIVE LOGITS
    ional
    1.28
    uary
    1.17
    uality
    1.12
    ual
    1.11
    uated
    1.02
    uate
    1.00
    ors
    0.96
    uating
    0.94
    ress
    0.90
    UAL
    0.90
    Activations Density 0.028%

    No Known Activations