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 6144
    5. 8-RES_FS6144-JB
    6. 4569
    Prev
    Next
    INDEX
    Explanations

    technical terms related to energy systems or processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    481
    +0.14
    0.6%
    288
    +0.13
    0.6%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.14
    564
    +0.13
    0.10
    40
    +0.11
    0.09
    Negative Logits
    perture
    -0.69
    igmat
    -0.69
    ukong
    -0.68
     Athe
    -0.66
    chant
    -0.65
     Roses
    -0.64
     Contrast
    -0.63
    irlf
    -0.63
    inosaur
    -0.63
     Honor
    -0.62
    POSITIVE LOGITS
     flows
    1.03
    flows
    1.00
    stuff
    0.95
     packets
    0.90
     supplies
    0.89
    bytes
    0.87
     molecules
    0.86
    flow
    0.85
     from
    0.84
     deposited
    0.84
    Activations Density 1.038%

    No Known Activations