© 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. 7130
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and software development, such as functions, variables, and patterns

    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
    255
    +0.15
    0.7%
    326
    +0.12
    0.5%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.15
    0.06
    326
    +0.12
    0.06
    540
    +0.11
    0.06
    Negative Logits
    Cele
    -0.84
     Bravo
    -0.76
    £
    -0.75
    waters
    -0.74
    Morning
    -0.74
    adult
    -0.73
    gov
    -0.70
    adelphia
    -0.69
    âĢİ
    -0.69
     Photograph
    -0.68
    POSITIVE LOGITS
     recursive
    1.39
     syntax
    1.29
     semantics
    1.26
     implementations
    1.22
     asynchronous
    1.21
     runtime
    1.20
     abstraction
    1.17
     synt
    1.16
     deprecated
    1.16
     ali
    1.15
    Activations Density 0.540%

    No Known Activations