© 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 EvalsExportsinterp-engineNEWAPI 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. 16249
    Prev
    Next
    INDEX
    Explanations

    details related to food and beverages

    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
    314
    +0.16
    0.7%
    152
    +0.11
    0.5%
    477
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.16
    0.07
    314
    +0.11
    0.02
    525
    +0.11
    0.04
    Negative Logits
     Salvador
    -0.66
     Galile
    -0.64
     Expend
    -0.64
     spont
    -0.63
     Nicarag
    -0.62
     Arabian
    -0.60
     notice
    -0.60
     Kurdish
    -0.59
     Rounds
    -0.59
     amaz
    -0.59
    POSITIVE LOGITS
    based
    1.33
    sized
    1.23
    bearing
    1.18
    shaped
    1.17
    maker
    1.16
    length
    1.15
    centric
    1.15
    related
    1.15
    holder
    1.13
    grab
    1.12
    Activations Density 0.099%

    No Known Activations