© 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. 12113
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events

    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
    +0.48
    2.5%
    266
    +0.21
    1.1%
    481
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.48
    0.07
    480
    +0.21
    0.02
    273
    +0.17
    0.06
    Negative Logits
    .","
    -0.62
     thereto
    -0.56
     respectively
    -0.53
     liqu
    -0.52
    itiz
    -0.51
    -"
    -0.51
     conduc
    -0.51
     behav
    -0.50
     â̦"
    -0.50
    Ïī
    -0.50
    POSITIVE LOGITS
    resa
    1.01
    xiety
    0.82
    odore
    0.82
    mosp
    0.71
    uckland
    0.64
    BSD
    0.63
     Facts
    0.62
    bidden
    0.61
     largeDownload
    0.61
    chieve
    0.61
    Activations Density 0.454%

    No Known Activations