© 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. 9044
    Prev
    Next
    INDEX
    Explanations

    time-related references, such as durations and specific points in time

    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
    17
    +0.10
    0.5%
    269
    +0.10
    0.5%
    545
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    657
    +0.10
    0.04
    269
    +0.10
    0.03
    344
    +0.10
    0.03
    Negative Logits
    ħĭ
    -0.98
    oiler
    -0.73
    idable
    -0.69
    irie
    -0.65
    iane
    -0.65
    idden
    -0.64
    ergy
    -0.63
    oci
    -0.63
    rored
    -0.63
    ntil
    -0.62
    POSITIVE LOGITS
     elapsed
    0.89
     (~
    0.87
     apiece
    0.87
     longer
    0.85
     convincing
    0.70
     digest
    0.70
     commute
    0.69
     consecut
    0.68
     patiently
    0.68
     trek
    0.67
    Activations Density 0.069%

    No Known Activations