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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19716
    Prev
    Next
    INDEX
    Explanations

    phrases related to building, development, and creation

    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
    620
    +0.09
    0.4%
    567
    +0.09
    0.4%
    551
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.09
    0.04
    49
    +0.09
    0.04
    665
    +0.09
    0.04
    Negative Logits
    listed
    -0.72
    calling
    -0.71
    rising
    -0.69
    started
    -0.66
     Words
    -0.64
    comments
    -0.64
     Thoughts
    -0.62
     Recorded
    -0.61
     Registrar
    -0.60
     Recon
    -0.60
    POSITIVE LOGITS
     withstand
    1.47
     maximize
    1.30
     accommodate
    1.29
     resemble
    1.20
     coincide
    1.16
     optimize
    1.14
     cope
    1.12
     emulate
    1.12
     comply
    1.12
     minimize
    1.10
    Activations Density 0.135%

    No Known Activations