© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1442
    Prev
    Next
    INDEX
    Explanations

    statements asserting the inclusion or cooperation of a specific group within a community

    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
    94
    +0.11
    0.5%
    626
    +0.10
    0.4%
    224
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.11
    0.04
    598
    +0.10
    0.03
    377
    +0.09
    0.05
    Negative Logits
    ravel
    -0.71
     Tanz
    -0.70
    ragon
    -0.69
     happ
    -0.65
    quer
    -0.65
    ords
    -0.65
    iates
    -0.64
    vet
    -0.63
     Olymp
    -0.63
    æ©
    -0.63
    POSITIVE LOGITS
     namely
    0.84
     "'
    0.75
     disbelief
    0.74
     disclaimer
    0.73
     congratulations
    0.72
     affirmation
    0.71
     skepticism
    0.70
     "...
    0.69
    Eat
    0.69
     humility
    0.68
    Activations Density 0.376%

    No Known Activations