© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5864
    Prev
    Next
    INDEX
    Explanations

    statements related to political events and controversies

    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
    640
    +0.32
    1.6%
    314
    +0.17
    0.8%
    480
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.32
    0.10
    143
    +0.17
    0.06
    6
    +0.11
    0.06
    Negative Logits
     tink
    -0.75
     estranged
    -0.72
     footing
    -0.72
    hement
    -0.70
     overth
    -0.69
     manoeuv
    -0.69
     scrap
    -0.69
     grouping
    -0.66
     upstairs
    -0.63
     home
    -0.63
    POSITIVE LOGITS
    ³³³³
    1.30
    ³³³³³³³³³³³³³³³³
    1.20
    ³³³
    1.18
    ³³³³³³³³
    1.17
    ³³
    1.05
    Posted
    1.04
    Synopsis
    1.00
    Disclaimer
    0.95
    Anonymous
    0.95
    posted
    0.94
    Activations Density 0.199%

    No Known Activations