© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19722
    Prev
    Next
    INDEX
    Explanations

    product names and prices

    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
    447
    +0.14
    0.6%
    124
    +0.10
    0.5%
    739
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.06
    232
    +0.10
    0.04
    739
    +0.10
    0.02
    Negative Logits
    theless
    -0.85
     pend
    -0.76
     lowly
    -0.72
    fortunately
    -0.69
     whence
    -0.69
     overtime
    -0.68
     reper
    -0.68
     proportional
    -0.68
     hurd
    -0.67
    ucl
    -0.67
    POSITIVE LOGITS
     Manager
    1.16
     Collection
    1.14
     Guide
    1.12
     Pack
    1.08
     Coup
    1.07
     Holder
    1.07
     Dates
    1.06
     Packs
    1.05
     Plugin
    1.04
     Scenes
    1.04
    Activations Density 0.244%

    No Known Activations