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. 5341
    Prev
    Next
    INDEX
    Explanations

    details related to legal cases and news articles

    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
    480
    +0.66
    8.2%
    373
    +0.17
    2.1%
    87
    +0.17
    2.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.66
    0.09
    266
    +0.17
    0.28
    373
    +0.17
    -0.18
    Negative Logits
    sic
    -0.25
    enegger
    -0.24
    Sov
    -0.24
    tein
    -0.23
    eus
    -0.22
    forth
    -0.21
    代
    -0.21
    âķIJ
    -0.20
    ngth
    -0.20
    flake
    -0.20
    POSITIVE LOGITS
     âĢº
    0.19
     Brend
    0.17
     GeForce
    0.16
     Belfast
    0.16
     Orioles
    0.16
     <<
    0.16
     Mana
    0.15
    isoft
    0.15
     Comics
    0.15
     Regina
    0.15
    Activations Density 10.119%

    No Known Activations