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 3072
    5. 8-RES_FS3072-JB
    6. 1838
    Prev
    Next
    INDEX
    Explanations

    names or titles given to specific systems, projects, or groups

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    77
    +0.12
    0.5%
    14
    +0.10
    0.4%
    677
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    647
    +0.12
    0.06
    77
    +0.10
    0.06
    37
    +0.10
    0.06
    Negative Logits
    SPONSORED
    -0.82
     baseman
    -0.72
    Constructed
    -0.71
     horr
    -0.63
     reassure
    -0.62
     horrified
    -0.62
     enjoyed
    -0.62
     dstg
    -0.61
    Edited
    -0.61
     tempted
    -0.61
    POSITIVE LOGITS
     "#
    0.93
     "
    0.93
     '
    0.89
     `
    0.80
     COP
    0.80
     Operation
    0.79
     ``
    0.78
     Fancy
    0.73
     Excellence
    0.71
     RED
    0.70
    Activations Density 0.868%

    No Known Activations