© 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. 4084
    Prev
    Next
    INDEX
    Explanations

    mentions of specific space-related terms and projects, such as the International Space Station (ISS) and space missions

    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
    +0.15
    0.7%
    203
    +0.10
    0.5%
    378
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.04
    115
    +0.10
    0.03
    575
    +0.10
    0.03
    Negative Logits
    geist
    -0.90
    ç
    -0.81
    epad
    -0.76
    arty
    -0.76
    ogle
    -0.76
    女
    -0.74
    Town
    -0.74
    ologne
    -0.72
    Ott
    -0.72
    estamp
    -0.69
    POSITIVE LOGITS
     astronauts
    1.36
     spacecraft
    1.36
     satellites
    1.23
     manned
    1.22
     missions
    1.20
     orbiting
    1.18
     refuel
    1.17
     aboard
    1.15
     astronaut
    1.12
     submarines
    1.04
    Activations Density 0.118%

    No Known Activations