© 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 49152
    9. 8-RES_FS49152-JB
    11. 45666
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" in various contexts, often indicating action or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    31
    +0.12
    0.5%
    718
    +0.11
    0.5%
    665
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.12
    0.03
    608
    +0.11
    0.03
    665
    +0.11
    0.03
    Negative Logits
    ħĭ
    -0.78
    IDA
    -0.68
    TION
    -0.67
     Advice
    -0.66
    ONSORED
    -0.64
     Caller
    -0.64
    resy
    -0.64
    tur
    -0.62
    Choice
    -0.62
     Editors
    -0.61
    POSITIVE LOGITS
     realize
    1.16
     arrive
    1.15
     reach
    1.12
     accumulate
    1.07
     accomplish
    1.07
     recover
    1.06
     settle
    1.06
     achieve
    1.05
     develop
    1.04
     overcome
    1.03
    Activations Density 0.041%

    No Known Activations