© 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 EvalsExportsinterp-engineNEWAPI 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. 21145
    Prev
    Next
    INDEX
    Explanations

    terms related to economics and pricing

    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
    87
    +0.20
    1.1%
    623
    +0.10
    0.5%
    464
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    730
    +0.20
    0.04
    90
    +0.10
    0.04
    500
    +0.09
    0.04
    Negative Logits
    é¾į
    -0.51
     Democr
    -0.47
     Dangerous
    -0.47
     counterpart
    -0.46
     Examination
    -0.46
     lightly
    -0.45
     presumptive
    -0.45
     tightened
    -0.43
    Ö¼
    -0.42
    APTER
    -0.42
    POSITIVE LOGITS
     etc
    1.34
    etc
    1.11
    âĢ¦)
    0.86
    whatever
    0.69
     respectively
    0.64
    ...)
    0.64
    âĢ¦.
    0.62
    âĢ¦
    0.62
     blah
    0.61
    anything
    0.60
    Activations Density 0.420%

    No Known Activations