Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 43283
    Prev
    Next
    INDEX
    Explanations

    phrases expressing gratitude and appreciation

    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
    220
    +0.10
    0.4%
    354
    +0.10
    0.4%
    230
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.10
    0.05
    354
    +0.10
    0.05
    183
    +0.09
    0.04
    Negative Logits
    toggle
    -0.92
    Enlarge
    -0.72
     guiName
    -0.72
     penet
    -0.63
    enum
    -0.62
     Mirage
    -0.61
    rones
    -0.61
     kinetic
    -0.60
    Answer
    -0.60
     arsen
    -0.60
    POSITIVE LOGITS
     thank
    1.33
     congratulate
    1.29
     thanked
    1.22
     congratulated
    1.17
     sincerely
    1.16
     grateful
    1.13
     THANK
    1.09
     apologize
    1.07
     appreciate
    1.06
     apologies
    1.06
    Activations Density 0.195%

    No Known Activations