© 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 12288
    9. 8-RES_FS12288-JB
    11. 1710
    Prev
    Next
    INDEX
    Explanations

    financial terms and concepts, particularly related to cryptocurrency and financial policy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    87
    +0.29
    1.5%
    513
    +0.12
    0.6%
    530
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.29
    -0.04
    756
    +0.12
    -0.04
    51
    +0.10
    0.07
    Negative Logits
     Latest
    -0.58
    Newsletter
    -0.56
    é¾į
    -0.53
    odore
    -0.53
    ropolitan
    -0.50
    includes
    -0.49
     consisted
    -0.48
     Courtesy
    -0.48
     excerpt
    -0.47
     âĢİ
    -0.47
    POSITIVE LOGITS
     worthwhile
    0.78
     eventual
    0.70
     future
    0.70
     manageable
    0.66
     overall
    0.66
     desired
    0.65
     subsequent
    0.64
     someday
    0.62
     prematurely
    0.59
    Conclusion
    0.59
    Activations Density 2.271%

    No Known Activations