© 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. 6334
    Prev
    Next
    INDEX
    Explanations

    words related to transportation infrastructure, specifically tunnels

    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
    +0.18
    0.9%
    515
    +0.14
    0.7%
    447
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.02
    515
    +0.14
    0.02
    41
    +0.14
    0.02
    Negative Logits
    aign
    -0.72
     Liberties
    -0.66
    metics
    -0.66
    itia
    -0.64
    orian
    -0.61
     ANGEL
    -0.61
     Latest
    -0.60
     CHO
    -0.59
    yright
    -0.58
    oln
    -0.58
    POSITIVE LOGITS
     tunnel
    1.00
     tunnels
    0.98
     dug
    0.89
    vision
    0.89
     entrances
    0.89
     boring
    0.88
     Tunnel
    0.83
    bed
    0.81
    ibur
    0.81
    nels
    0.79
    Activations Density 0.021%

    No Known Activations