© 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 EvalsExportsinterp-engineNEWAPI 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. 16834
    Prev
    Next
    INDEX
    Explanations

    terms related to vehicle components and functions, particularly focusing on braking systems

    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
    +0.13
    0.6%
    316
    +0.11
    0.5%
    468
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.02
    288
    +0.11
    0.02
    678
    +0.10
    0.02
    Negative Logits
    swick
    -0.83
     Flavoring
    -0.83
    itutional
    -0.76
    aldo
    -0.76
    iverse
    -0.76
    entious
    -0.73
    estine
    -0.71
    sted
    -0.70
    onga
    -0.70
    arios
    -0.70
    POSITIVE LOGITS
     pedal
    1.32
     braking
    1.21
     brakes
    1.16
     pedals
    1.15
     brake
    1.10
     pads
    1.00
     levers
    0.99
     booster
    0.89
     subsystem
    0.86
     malfunction
    0.85
    Activations Density 0.053%

    No Known Activations