© 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. 18410
    Prev
    Next
    INDEX
    Explanations

    references to business operations or deals, particularly in the context of financial transactions or negotiations

    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
    393
    +0.17
    0.8%
    362
    +0.16
    0.8%
    608
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.17
    0.17
    608
    +0.16
    0.14
    393
    +0.14
    0.12
    Negative Logits
    hari
    -0.73
    £ı
    -0.69
    govtrack
    -0.69
    aves
    -0.67
    wine
    -0.64
    ornings
    -0.64
    arate
    -0.64
    ictionary
    -0.63
    asketball
    -0.61
    fg
    -0.61
    POSITIVE LOGITS
     latter
    1.22
     nascent
    1.09
     latest
    1.07
     burgeoning
    1.06
     fledgling
    1.05
     embattled
    1.04
     remainder
    1.03
     offending
    1.01
     same
    1.01
     elusive
    0.98
    Activations Density 0.856%

    No Known Activations