© 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. 8657
    Prev
    Next
    INDEX
    Explanations

    instructions related to setting up software environments

    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
    4
    +0.11
    0.5%
    373
    +0.11
    0.5%
    326
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.05
    60
    +0.11
    0.04
    534
    +0.10
    0.03
    Negative Logits
    ĸļ
    -0.96
    Narr
    -0.72
     emotional
    -0.71
    iday
    -0.70
     emotion
    -0.70
     flung
    -0.69
     laughs
    -0.68
     tears
    -0.67
    fashion
    -0.67
     exhilar
    -0.67
    POSITIVE LOGITS
     installed
    1.42
     install
    1.33
     installation
    1.25
     sudo
    1.24
     uninstall
    1.24
     installs
    1.23
     configure
    1.23
    installed
    1.21
     configured
    1.18
     Install
    1.16
    Activations Density 0.389%

    No Known Activations