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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 2145
    Prev
    Next
    INDEX
    Explanations

    a mix of diverse topics, like sports, politics, and video games

    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
    640
    +0.28
    1.4%
    160
    +0.18
    0.9%
    314
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.28
    0.10
    160
    +0.18
    0.10
    442
    +0.17
    0.08
    Negative Logits
     agre
    -0.86
     ende
    -0.84
     compr
    -0.82
     tiss
    -0.81
     describ
    -0.81
     destro
    -0.78
     downstream
    -0.78
     princ
    -0.77
     streng
    -0.77
     accomp
    -0.76
    POSITIVE LOGITS
    Topics
    1.39
    Advertisements
    1.34
    Topic
    1.34
    Joined
    1.32
    Offline
    1.31
    Enlarge
    1.25
    Posts
    1.25
    Language
    1.21
    References
    1.21
    Legendary
    1.20
    Activations Density 0.219%

    No Known Activations