© 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. 10344
    Prev
    Next
    INDEX
    Explanations

    mentions of notable individuals and their roles in various events or environments

    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
    37
    +0.12
    0.5%
    314
    +0.11
    0.5%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.12
    0.06
    718
    +0.11
    0.06
    499
    +0.10
    0.04
    Negative Logits
     stabilization
    -0.73
    teness
    -0.69
     overload
    -0.69
     totality
    -0.68
     puls
    -0.68
     progression
    -0.66
     Tok
    -0.66
     sweeps
    -0.66
     multiplication
    -0.66
     Flow
    -0.65
    POSITIVE LOGITS
     endorsed
    1.15
    enegger
    1.11
     assassinated
    1.11
     vetoed
    1.08
    osponsors
    1.05
     filib
    1.02
     endorsing
    1.01
     famously
    1.01
     denounced
    1.00
     impe
    1.00
    Activations Density 0.447%

    No Known Activations