© 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. 20470
    Prev
    Next
    INDEX
    Explanations

    religious or spiritual content-related text

    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
    314
    +0.19
    0.9%
    640
    +0.18
    0.8%
    447
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.19
    0.11
    6
    +0.18
    0.09
    160
    +0.15
    0.09
    Negative Logits
     interns
    -0.96
     tech
    -0.93
     offshore
    -0.92
     diving
    -0.91
     hosting
    -0.89
     freel
    -0.89
     quir
    -0.88
     outsourcing
    -0.87
     scra
    -0.87
     cybersecurity
    -0.85
    POSITIVE LOGITS
    Thus
    1.56
    CHAPTER
    1.55
    Therefore
    1.41
    Chapter
    1.38
    VII
    1.26
    Notes
    1.18
    III
    1.18
    Faith
    1.17
    THE
    1.16
    Letter
    1.16
    Activations Density 0.328%

    No Known Activations