© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9479
    Prev
    Next
    INDEX
    Explanations

    complex and radical concepts or ideas

    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
    362
    +0.12
    0.6%
    469
    +0.10
    0.5%
    321
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.04
    455
    +0.10
    0.04
    408
    +0.10
    0.04
    Negative Logits
    owell
    -0.69
    FORE
    -0.68
    isha
    -0.67
     multiplied
    -0.67
    Jump
    -0.67
    SEA
    -0.66
    ledge
    -0.65
    ructose
    -0.62
    along
    -0.62
    essler
    -0.62
    POSITIVE LOGITS
     than
    1.38
     versions
    1.17
    than
    1.13
     Than
    1.07
     forms
    1.04
     alternatives
    1.00
     sounding
    1.00
     version
    0.99
     ones
    0.97
     aspects
    0.95
    Activations Density 0.133%

    No Known Activations