© 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 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. 12209
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic and technological advancements

    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
    304
    +0.14
    0.6%
    21
    +0.12
    0.5%
    98
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.14
    0.04
    750
    +0.12
    0.03
    98
    +0.11
    0.04
    Negative Logits
     herself
    -0.65
    hee
    -0.63
    ourage
    -0.59
     teammates
    -0.58
     himself
    -0.57
    elson
    -0.57
     staffer
    -0.57
     garnered
    -0.57
     Packs
    -0.57
     pseudonym
    -0.56
    POSITIVE LOGITS
     ourselves
    0.91
     reckoning
    0.88
     "$:/
    0.85
     unch
    0.82
     witnessing
    0.76
    enment
    0.76
    htaking
    0.75
     electing
    0.71
    ometers
    0.71
    entin
    0.71
    Activations Density 0.299%

    No Known Activations