© 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. 1937
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by positive expressions to describe communal experiences or values

    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
    330
    +0.12
    0.5%
    116
    +0.11
    0.5%
    730
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.12
    0.05
    733
    +0.11
    0.04
    389
    +0.11
    0.04
    Negative Logits
    achus
    -0.79
    hood
    -0.74
    cation
    -0.72
    cohol
    -0.70
    ternity
    -0.70
    iness
    -0.69
    let
    -0.68
    runtime
    -0.68
    erate
    -0.68
    atform
    -0.68
    POSITIVE LOGITS
     guys
    1.06
     kinds
    0.98
     sorts
    0.95
     fellows
    0.94
     truths
    0.87
     days
    0.85
     gentlemen
    0.84
     facts
    0.83
     folks
    0.80
     types
    0.77
    Activations Density 0.097%

    No Known Activations