© 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. 13847
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to consuming 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
    430
    +0.12
    0.5%
    373
    +0.11
    0.5%
    721
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.12
    0.05
    729
    +0.11
    0.04
    426
    +0.11
    0.04
    Negative Logits
    etheless
    -0.98
    Ĥª
    -0.88
    ¬¼
    -0.84
    £ı
    -0.81
    İĭ
    -0.80
    ibrary
    -0.77
    itionally
    -0.73
    erity
    -0.73
    ramid
    -0.72
    »Ĵ
    -0.71
    POSITIVE LOGITS
     says
    1.18
     whispered
    1.06
     reads
    1.05
     replied
    1.04
     muttered
    1.03
     said
    1.03
    said
    1.03
     exclaimed
    1.02
     recalls
    0.98
     joked
    0.98
    Activations Density 0.087%

    No Known Activations