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 24576
    5. 8-RES_FS24576-JB
    6. 21411
    Prev
    Next
    INDEX
    Explanations

    short phrases related to sending a message or signal

    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
    654
    +0.11
    0.5%
    298
    +0.11
    0.5%
    463
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.11
    0.03
    654
    +0.11
    0.02
    567
    +0.09
    0.02
    Negative Logits
    uncture
    -0.72
    ById
    -0.70
    iqueness
    -0.69
     Dealer
    -0.66
    âĶĢâĶĢâĶĢâĶĢ
    -0.66
    ancy
    -0.63
    ater
    -0.63
    san
    -0.63
    acles
    -0.62
    antry
    -0.62
    POSITIVE LOGITS
     message
    1.09
     messages
    0.96
     messenger
    0.94
     condolences
    0.93
     Message
    0.91
     letter
    0.87
    message
    0.84
     reinforcements
    0.84
     mail
    0.84
     congrat
    0.84
    Activations Density 0.133%

    No Known Activations