© 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. 12374
    Prev
    Next
    INDEX
    Explanations

    conversations and negotiations related to contracts

    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
    23
    +0.11
    0.5%
    640
    +0.10
    0.4%
    481
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.11
    0.07
    719
    +0.10
    0.06
    474
    +0.09
    0.05
    Negative Logits
     Mous
    -0.84
     dispers
    -0.79
     shroud
    -0.76
     shack
    -0.76
     Belg
    -0.75
     assemb
    -0.73
     cottage
    -0.70
     scrambling
    -0.70
     tram
    -0.69
     range
    -0.69
    POSITIVE LOGITS
    ľ
    1.69
    ª
    1.46
    ¤
    1.43
    ¡
    1.43
    Ķ
    1.40
    Ŀ
    1.35
    ĺ
    1.34
    ļ
    1.33
    į
    1.33
    Ľ
    1.32
    Activations Density 0.056%

    No Known Activations