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. 19114
    Prev
    Next
    INDEX
    Explanations

    names of companies

    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
    205
    +0.10
    0.4%
    481
    +0.09
    0.4%
    677
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    647
    +0.10
    0.03
    677
    +0.09
    0.03
    37
    +0.09
    0.03
    Negative Logits
    SPONSORED
    -0.70
    jee
    -0.69
    inth
    -0.69
    âķIJâķIJ
    -0.67
    -------------
    -0.65
     practiced
    -0.65
     isolate
    -0.64
    olate
    -0.64
    midt
    -0.62
    Edited
    -0.62
    POSITIVE LOGITS
     "#
    0.81
     Operation
    0.80
     Trace
    0.80
     RED
    0.73
     Fug
    0.71
     Amb
    0.70
     Sleeping
    0.70
     Ares
    0.69
     Fancy
    0.69
     Vert
    0.69
    Activations Density 0.051%

    No Known Activations