© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1880
    Prev
    Next
    INDEX
    Explanations

    references to technical specifications and modifications

    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
    +0.40
    2.1%
    447
    +0.26
    1.4%
    481
    +0.22
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.40
    0.11
    575
    +0.26
    0.10
    480
    +0.22
    0.02
    Negative Logits
    atever
    -0.54
    rique
    -0.54
     charism
    -0.54
    âĸ¬
    -0.53
    ãĤ©
    -0.51
    enegger
    -0.50
     thous
    -0.49
     Azerb
    -0.48
    ONSORED
    -0.48
     Thing
    -0.47
    POSITIVE LOGITS
    mith
    1.24
    paces
    1.03
    pace
    1.03
    chool
    1.01
    creen
    1.00
    peed
    0.98
    hip
    0.96
    pring
    0.95
    heet
    0.94
    ynthesis
    0.93
    Activations Density 0.736%

    No Known Activations