© 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. 20754
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations or organizations, specifically "Kings"

    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
    223
    +0.11
    0.5%
    546
    +0.10
    0.4%
    509
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.11
    0.01
    657
    +0.10
    0.01
    700
    +0.09
    0.01
    Negative Logits
    awaru
    -0.79
    ierrez
    -0.74
    GoldMagikarp
    -0.70
    zzle
    -0.70
    eredith
    -0.68
    schild
    -0.67
    llah
    -0.62
     dissemination
    -0.61
    ATIONAL
    -0.61
     periodic
    -0.60
    POSITIVE LOGITS
    guard
    1.03
    Kings
    1.02
    hip
    0.99
    north
    0.98
    ley
    0.94
    bury
    0.94
    leys
    0.92
    wick
    0.91
    lake
    0.89
    olver
    0.87
    Activations Density 0.012%

    No Known Activations