© 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. 8732
    Prev
    Next
    INDEX
    Explanations

    the verb "navigate" along with its variations and related words

    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
    447
    +0.14
    0.7%
    255
    +0.11
    0.5%
    151
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.14
    0.01
    587
    +0.11
    0.01
    255
    +0.11
    0.01
    Negative Logits
    rie
    -0.72
    eye
    -0.72
    riter
    -0.71
    ¢
    -0.71
    rites
    -0.68
    venge
    -0.67
    onement
    -0.66
    si
    -0.66
    endi
    -0.65
    FORE
    -0.65
    POSITIVE LOGITS
     navigating
    0.97
     navigate
    0.94
     uphill
    0.91
     thru
    0.85
     through
    0.84
     paths
    0.82
     navig
    0.82
     labyrinth
    0.76
     menus
    0.72
     treacherous
    0.72
    Activations Density 0.025%

    No Known Activations