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. 311
    Prev
    Next
    INDEX
    Explanations

    descriptions related to physical attributes and behaviors of birds

    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
    738
    +0.11
    0.5%
    544
    +0.10
    0.4%
    384
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    620
    +0.11
    0.02
    544
    +0.10
    0.03
    756
    +0.09
    -0.03
    Negative Logits
     Logged
    -0.62
     Spa
    -0.60
     Wolfe
    -0.60
     Tuls
    -0.59
     Ange
    -0.59
     Sparks
    -0.59
     Grateful
    -0.58
     Grassley
    -0.58
     Grayson
    -0.58
     Harley
    -0.58
    POSITIVE LOGITS
    trak
    0.96
    arser
    0.92
     likewise
    0.79
     versa
    0.77
    ocre
    0.74
    oother
    0.73
     similarly
    0.72
    etheless
    0.69
    iltr
    0.69
     opposite
    0.68
    Activations Density 1.009%

    No Known Activations