© 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. 19622
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical details or actions, specifically within the contexts of programming and web development

    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
    238
    +0.10
    0.5%
    362
    +0.10
    0.5%
    166
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    60
    +0.10
    0.04
    61
    +0.10
    0.03
    238
    +0.10
    0.03
    Negative Logits
    EMBER
    -0.73
    ãģ®éŃĶ
    -0.69
    Asia
    -0.64
    Tact
    -0.62
    nant
    -0.62
    erate
    -0.62
    §
    -0.62
    ongyang
    -0.61
     Monthly
    -0.61
    undown
    -0.60
    POSITIVE LOGITS
    draw
    1.30
    stood
    1.29
    drawn
    1.27
     apologies
    1.17
     regard
    1.17
     regards
    1.09
     hindsight
    1.09
     caveats
    1.07
     respect
    1.02
    standing
    1.00
    Activations Density 0.110%

    No Known Activations