© 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. 19707
    Prev
    Next
    INDEX
    Explanations

    references to computer science, including courses, professors, enrollment statistics, and related predictions

    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
    447
    +0.10
    0.5%
    723
    +0.10
    0.5%
    524
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.05
    524
    +0.10
    0.05
    575
    +0.10
    0.04
    Negative Logits
    pload
    -0.92
    ãĥ´
    -0.87
    berry
    -0.83
    thumbnails
    -0.79
    éĹĺ
    -0.75
    SN
    -0.74
    ãĥĥãĥī
    -0.72
    é¾įåĸļ士
    -0.71
     Himself
    -0.69
     Corpse
    -0.68
    POSITIVE LOGITS
     expert
    1.10
     experts
    1.10
     expertise
    1.06
     specialist
    1.06
     professionals
    1.03
     specialists
    1.00
     doctoral
    0.95
     practitioner
    0.95
     guru
    0.92
     graduate
    0.89
    Activations Density 0.137%

    No Known Activations