© 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. 16142
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions and debates

    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
    +0.14
    0.6%
    393
    +0.14
    0.6%
    36
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.07
    393
    +0.14
    0.05
    636
    +0.11
    0.04
    Negative Logits
    aurus
    -0.69
    ngth
    -0.67
    âĢł
    -0.65
    Layer
    -0.65
    *,
    -0.63
    let
    -0.63
    lessly
    -0.61
    Iterator
    -0.60
    AppData
    -0.60
    fully
    -0.59
    POSITIVE LOGITS
     topic
    1.25
     basis
    1.23
     behalf
    1.21
     eve
    1.20
     sidelines
    1.10
     heels
    1.09
     occasion
    1.09
     grounds
    1.07
     merits
    1.02
     subject
    1.01
    Activations Density 0.179%

    No Known Activations