© 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. 19381
    Prev
    Next
    INDEX
    Explanations

    instances of the word "money"

    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
    352
    +0.12
    0.6%
    351
    +0.11
    0.5%
    488
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.12
    0.04
    351
    +0.11
    0.03
    444
    +0.09
    0.03
    Negative Logits
    ICLE
    -0.81
    spect
    -0.70
     Halls
    -0.65
    Minor
    -0.65
     Hug
    -0.63
     Frem
    -0.63
    REDACTED
    -0.60
     Fuk
    -0.60
     Klu
    -0.60
    Hug
    -0.59
    POSITIVE LOGITS
     laundering
    1.37
     invested
    0.97
     ($
    0.92
    dollar
    0.90
    bags
    0.89
     spent
    0.87
    -$
    0.86
     allocated
    0.86
     owed
    0.85
     dollars
    0.84
    Activations Density 0.035%

    No Known Activations