© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12022
    Prev
    Next
    INDEX
    Explanations

    references to the term "Golden"

    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
    459
    +0.14
    0.6%
    421
    +0.13
    0.6%
    472
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.14
    0.02
    472
    +0.13
    0.02
    525
    +0.12
    0.02
    Negative Logits
    Downloadha
    -0.87
    mble
    -0.81
    tics
    -0.81
    xus
    -0.77
    akeru
    -0.77
    ional
    -0.75
    tic
    -0.74
    kers
    -0.71
    alach
    -0.71
    nces
    -0.70
    POSITIVE LOGITS
     retri
    1.01
     retrie
    0.95
    rod
    0.93
     Age
    0.88
     showers
    0.80
     Gate
    0.79
     Globe
    0.77
     calf
    0.75
     Triangle
    0.75
     Eagles
    0.74
    Activations Density 0.017%

    No Known Activations