© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 768
    9. 8-RES_FS768-JB
    11. 670
    Prev
    Next
    INDEX
    Explanations

    sporting event-related phrases and terminology

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    760
    +0.11
    0.5%
    313
    +0.10
    0.5%
    680
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    739
    +0.11
    0.07
    498
    +0.10
    0.13
    377
    +0.10
    0.17
    Negative Logits
    ['
    -0.75
    existent
    -0.69
    ibles
    -0.66
    "},"
    -0.66
    ãĥı
    -0.63
     Canaveral
    -0.62
    claimed
    -0.60
     Reincarnated
    -0.60
    æ©
    -0.59
     valued
    -0.59
    POSITIVE LOGITS
     summarize
    1.23
     recap
    1.22
     summar
    1.07
     briefly
    1.05
     disclaimer
    1.03
     summarizes
    1.01
     excerpt
    1.00
     nutshell
    0.99
     spoiler
    0.99
     caveat
    0.98
    Activations Density 6.770%

    No Known Activations