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

    Neuronpedia

    Jacobian LensNEW
    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. 10711
    Prev
    Next
    INDEX
    Explanations

    syntactically complex sentences ending with punctuation other than a period

    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
    480
    +0.26
    1.3%
    447
    +0.17
    0.8%
    679
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.26
    0.12
    679
    +0.17
    0.11
    640
    +0.14
    0.11
    Negative Logits
     retri
    -0.81
    emon
    -0.70
    annabin
    -0.61
     pocket
    -0.61
     prest
    -0.60
    iencies
    -0.60
     disg
    -0.60
     restored
    -0.58
     manned
    -0.58
     obedient
    -0.57
    POSITIVE LOGITS
     Specifically
    1.47
    Firstly
    1.27
    Specifically
    1.20
     Firstly
    1.20
     Particularly
    1.14
     Especially
    1.13
     Personally
    1.11
     Basically
    1.02
     Topics
    1.01
    Personally
    0.99
    Activations Density 0.631%

    No Known Activations