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

    Neuronpedia

    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. 18547
    Prev
    Next
    INDEX
    Explanations

    the word 'the'

    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
    393
    +0.19
    0.9%
    608
    +0.13
    0.6%
    362
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.19
    0.05
    381
    +0.13
    0.04
    362
    +0.13
    0.04
    Negative Logits
    iture
    -0.97
     thereof
    -0.74
    nance
    -0.68
    ENCE
    -0.67
    Rex
    -0.66
     Zup
    -0.65
    anse
    -0.64
    FS
    -0.63
    heit
    -0.63
    ESSION
    -0.63
    POSITIVE LOGITS
     earliest
    1.25
     oldest
    1.19
     hottest
    1.13
     busiest
    1.12
     strongest
    1.11
     coolest
    1.11
     heaviest
    1.08
     largest
    1.07
     finest
    1.05
     fastest
    1.05
    Activations Density 0.075%

    No Known Activations