© 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. 7522
    Prev
    Next
    INDEX
    Explanations

    phrases related to urban planning and development

    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
    272
    +0.11
    0.5%
    446
    +0.09
    0.4%
    354
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.05
    272
    +0.09
    0.03
    431
    +0.09
    0.03
    Negative Logits
    note
    -0.74
    FML
    -0.74
    ér
    -0.73
     Advertisement
    -0.70
    ento
    -0.69
    hement
    -0.67
    aches
    -0.67
    arov
    -0.65
    arse
    -0.65
    Reporting
    -0.64
    POSITIVE LOGITS
     someday
    1.50
     future
    1.40
     tomorrow
    1.16
     impending
    1.13
     doom
    1.11
     imminent
    1.11
     eventual
    1.10
    future
    1.08
     futures
    1.04
     hereafter
    1.00
    Activations Density 0.312%

    No Known Activations