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. 2261
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms related to anatomy, weaponry, and technology

    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
    447
    +0.16
    0.8%
    420
    +0.14
    0.7%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.16
    0.11
    515
    +0.14
    0.09
    655
    +0.10
    0.09
    Negative Logits
    checking
    -0.76
    wrong
    -0.67
    lag
    -0.64
    avin
    -0.64
    osen
    -0.64
    ede
    -0.63
    error
    -0.62
    Knowing
    -0.62
    truth
    -0.62
    reality
    -0.62
    POSITIVE LOGITS
     versatile
    1.07
     housed
    1.04
     functionally
    1.03
     comprised
    1.00
     capable
    0.99
     primarily
    0.98
     composed
    0.97
     easily
    0.96
     extremely
    0.96
     mainly
    0.95
    Activations Density 2.563%

    No Known Activations