© 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. 10396
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms, as well as names of companies and organizations

    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
    480
    +0.54
    2.9%
    266
    +0.14
    0.8%
    87
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.54
    0.02
    266
    +0.14
    0.06
    247
    +0.10
    0.05
    Negative Logits
    depending
    -0.64
     idle
    -0.62
     silence
    -0.59
     mute
    -0.59
     awa
    -0.57
     stride
    -0.57
     arsen
    -0.54
     narrower
    -0.54
     stroke
    -0.53
     unfavorable
    -0.53
    POSITIVE LOGITS
     Ltd
    1.06
     LLC
    0.95
     Solutions
    0.86
     LLP
    0.83
     Facility
    0.81
     Initiative
    0.80
     Limited
    0.80
     Architects
    0.80
    âĦ¢
    0.79
     LTD
    0.79
    Activations Density 0.434%

    No Known Activations