© 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. 1435
    Prev
    Next
    INDEX
    Explanations

    text related to political topics and news

    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
    6
    +0.19
    0.9%
    640
    +0.18
    0.8%
    679
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.19
    0.13
    679
    +0.18
    0.10
    640
    +0.15
    0.10
    Negative Logits
     attrition
    -1.12
     acquisitions
    -0.97
     affili
    -0.96
     accommodation
    -0.94
     footing
    -0.91
     enrol
    -0.88
     wage
    -0.87
     unrest
    -0.87
     casualty
    -0.87
     commodities
    -0.87
    POSITIVE LOGITS
     Apparently
    1.32
     Basically
    1.28
     Seems
    1.25
     Oops
    1.23
     Sadly
    1.21
     Congratulations
    1.20
     Seriously
    1.18
     Needless
    1.17
     It
    1.16
     Originally
    1.15
    Activations Density 0.406%

    No Known Activations