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. 984
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people mentioned in news articles

    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
    762
    +0.11
    0.5%
    502
    +0.11
    0.5%
    55
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.11
    0.07
    477
    +0.11
    0.05
    502
    +0.11
    0.06
    Negative Logits
     Colonial
    -0.64
    piring
    -0.61
    entary
    -0.60
     exponential
    -0.60
     abound
    -0.59
     IB
    -0.58
     Stats
    -0.58
    rawdownloadcloneembedreportprint
    -0.58
     Factory
    -0.57
     flowing
    -0.57
    POSITIVE LOGITS
    'd
    1.28
     regretted
    1.08
     personally
    1.06
     thinks
    1.01
     wished
    1.01
     knew
    0.99
    zbollah
    0.98
     believes
    0.95
     intends
    0.95
     hadn
    0.94
    Activations Density 0.221%

    No Known Activations