© 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. 209
    Prev
    Next
    INDEX
    Explanations

    words related to places or locations

    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
    288
    +0.14
    0.6%
    651
    +0.11
    0.5%
    231
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.14
    0.01
    288
    +0.11
    0.01
    231
    +0.10
    0.01
    Negative Logits
    appa
    -0.83
    ucket
    -0.76
    ulate
    -0.75
    igan
    -0.74
    hemat
    -0.72
    inventoryQuantity
    -0.72
    morph
    -0.71
    ooks
    -0.70
    conn
    -0.70
    aps
    -0.69
    POSITIVE LOGITS
     destination
    1.09
     destinations
    1.00
     Destination
    0.94
     whence
    0.87
     traveler
    0.83
     location
    0.74
    finder
    0.71
     airport
    0.70
     locale
    0.69
     Airlines
    0.66
    Activations Density 0.026%

    No Known Activations