© 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. 16691
    Prev
    Next
    INDEX
    Explanations

    prepositions and specific articles in text

    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
    113
    +0.14
    0.7%
    276
    +0.11
    0.5%
    608
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.14
    0.06
    113
    +0.11
    0.04
    276
    +0.10
    0.04
    Negative Logits
     hospitality
    -0.65
     licences
    -0.65
    soDeliveryDate
    -0.64
     licenses
    -0.62
    TD
    -0.60
     phased
    -0.59
     outgoing
    -0.58
     Photographer
    -0.57
     vows
    -0.56
     franch
    -0.56
    POSITIVE LOGITS
    pless
    1.14
    ggles
    1.00
    othy
    0.99
    wered
    0.90
     conclusions
    0.85
     conserve
    0.84
     maximize
    0.83
    ppers
    0.83
     accommodate
    0.82
    pload
    0.81
    Activations Density 0.153%

    No Known Activations