© 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. 6743
    Prev
    Next
    INDEX
    Explanations

    words related to transportation and movement of people or goods

    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
    574
    +0.10
    0.5%
    599
    +0.10
    0.5%
    439
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.10
    0.04
    439
    +0.10
    0.04
    230
    +0.10
    0.03
    Negative Logits
    aces
    -0.69
     Accuracy
    -0.67
    Fram
    -0.67
     stance
    -0.67
     brow
    -0.66
     eyebrow
    -0.65
     nomine
    -0.65
     shading
    -0.64
    ellen
    -0.63
    soft
    -0.61
    POSITIVE LOGITS
     cargo
    1.19
     passengers
    1.12
     shipments
    1.11
     goods
    1.09
     migrants
    1.07
     supplies
    1.04
     freight
    1.01
     shipment
    0.96
     transporting
    0.93
     containers
    0.93
    Activations Density 0.277%

    No Known Activations