© 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 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. 17539
    Prev
    Next
    INDEX
    Explanations

    words related to transportation, urban infrastructure, and manual labor tasks

    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
    415
    +0.12
    0.5%
    497
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.12
    0.08
    415
    +0.11
    0.06
    225
    +0.10
    0.07
    Negative Logits
    ãĤ¨ãĥ«
    -0.79
    ãĥį
    -0.79
    ITION
    -0.78
    ãĤ¢ãĥ«
    -0.76
    Region
    -0.73
    ?????-
    -0.72
    STER
    -0.72
    é¾įåĸļ士
    -0.71
    METHOD
    -0.71
    ãĥ´
    -0.71
    POSITIVE LOGITS
     abound
    0.97
    hips
    0.94
     gal
    0.91
     etc
    0.88
     and
    0.87
    mith
    0.85
    hops
    0.80
    ynthesis
    0.79
    etting
    0.79
    avers
    0.78
    Activations Density 0.456%

    No Known Activations