© 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. 77
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terminology, especially related to nuclear energy and political agreements

    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
    430
    +0.14
    0.6%
    525
    +0.12
    0.6%
    496
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.14
    0.06
    288
    +0.12
    0.05
    396
    +0.12
    0.04
    Negative Logits
     queen
    -0.81
     queens
    -0.78
     crawl
    -0.75
     bells
    -0.74
     king
    -0.73
     chains
    -0.72
     craw
    -0.71
     sides
    -0.71
     haunt
    -0.70
    rams
    -0.70
    POSITIVE LOGITS
     Development
    1.28
     Assessment
    1.25
     Identification
    1.23
     Affairs
    1.23
     Services
    1.22
     Solutions
    1.18
     Investigations
    1.17
     Definition
    1.17
     Partnership
    1.16
     Advisory
    1.16
    Activations Density 0.179%

    No Known Activations