© 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 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. 7603
    Prev
    Next
    INDEX
    Explanations

    words related to user interactions in websites or software programs

    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
    430
    +0.12
    0.5%
    119
    +0.11
    0.5%
    718
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    653
    +0.12
    0.03
    97
    +0.11
    0.03
    119
    +0.11
    0.03
    Negative Logits
    amer
    -0.69
     Baptist
    -0.69
     Lutheran
    -0.67
     Vaugh
    -0.66
    SourceFile
    -0.65
    western
    -0.65
    hovah
    -0.64
    forth
    -0.60
     Maid
    -0.60
     Tempest
    -0.60
    POSITIVE LOGITS
     interface
    1.08
    pace
    1.01
     interfaces
    1.01
    interface
    0.99
    cript
    0.93
     Interface
    0.87
    base
    0.86
    Agent
    0.83
    agent
    0.81
    hip
    0.78
    Activations Density 0.042%

    No Known Activations