© 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. 17710
    Prev
    Next
    INDEX
    Explanations

    descriptions of social, political, and economic issues, especially related to education, healthcare, and societal transformations

    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
    450
    +0.12
    0.6%
    85
    +0.10
    0.5%
    616
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.12
    0.03
    537
    +0.10
    0.02
    616
    +0.10
    0.02
    Negative Logits
     Cassidy
    -0.68
     Collider
    -0.67
     AVG
    -0.67
     Defenders
    -0.63
     Fiesta
    -0.63
    ãĥ£
    -0.63
     Brav
    -0.61
     turbulence
    -0.61
     Aether
    -0.61
     Situation
    -0.60
    POSITIVE LOGITS
    eight
    1.35
    six
    1.34
    seven
    1.34
    five
    1.34
    nine
    1.30
    four
    1.24
    three
    1.16
    percent
    1.14
    two
    1.14
    undreds
    1.13
    Activations Density 0.032%

    No Known Activations