© 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. 1257
    Prev
    Next
    INDEX
    Explanations

    vocal-related terms, such as vocalists and vocal ensembles

    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
    99
    +0.13
    0.6%
    216
    +0.11
    0.5%
    415
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.13
    0.01
    711
    +0.11
    0.01
    505
    +0.10
    0.01
    Negative Logits
     Reincarn
    -0.91
    agher
    -0.87
    awaru
    -0.86
    uden
    -0.82
    busters
    -0.78
    hig
    -0.71
     Neighbor
    -0.68
     Papers
    -0.67
    rentice
    -0.67
    20439
    -0.66
    POSITIVE LOGITS
    izations
    1.36
    isations
    1.24
     cords
    1.24
    izers
    1.17
    izing
    1.16
    izes
    1.12
    ized
    1.09
     chords
    1.08
    izer
    1.08
    ists
    1.06
    Activations Density 0.017%

    No Known Activations