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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18777
    Prev
    Next
    INDEX
    Explanations

    information related to routes or directions

    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
    160
    +0.11
    0.5%
    515
    +0.10
    0.5%
    130
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.11
    0.02
    130
    +0.10
    0.01
    686
    +0.10
    0.01
    Negative Logits
    uster
    -0.94
    iaries
    -0.81
    luaj
    -0.81
    endi
    -0.78
    usters
    -0.78
     Hots
    -0.77
    ukes
    -0.76
    oru
    -0.71
    obil
    -0.70
    oice
    -0.70
    POSITIVE LOGITS
     routes
    1.05
    finding
    0.95
    route
    0.94
    Route
    0.94
     route
    0.93
    WAYS
    0.84
     routing
    0.81
     Roads
    0.81
    nels
    0.80
    book
    0.76
    Activations Density 0.027%

    No Known Activations