© 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. 19442
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Turner"

    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
    447
    +0.14
    0.6%
    288
    +0.12
    0.5%
    99
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    525
    +0.14
    0.01
    326
    +0.12
    0.01
    683
    +0.12
    0.01
    Negative Logits
    uncle
    -0.79
    places
    -0.75
    inct
    -0.75
    alg
    -0.74
    acebook
    -0.73
    lehem
    -0.73
    dyl
    -0.71
    lyak
    -0.71
    ortality
    -0.70
    arial
    -0.70
    POSITIVE LOGITS
     Broadcasting
    0.96
    worth
    0.78
    sonian
    0.78
     Turner
    0.75
    mington
    0.72
    ston
    0.70
    stown
    0.68
    ples
    0.68
     Field
    0.67
     Motorsport
    0.67
    Activations Density 0.025%

    No Known Activations