© 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. 19675
    Prev
    Next
    INDEX
    Explanations

    mentions of puppet-related activities

    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
    679
    +0.13
    0.6%
    447
    +0.12
    0.6%
    48
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.01
    288
    +0.12
    0.02
    48
    +0.11
    0.01
    Negative Logits
    20439
    -0.74
    ãĥ³ãĤ¸
    -0.67
    âĸ¬
    -0.65
     DATA
    -0.64
    mber
    -0.63
    ARB
    -0.63
     Dynamics
    -0.61
     uncertainties
    -0.60
     Grind
    -0.59
    nings
    -0.59
    POSITIVE LOGITS
     pupp
    0.97
     puppet
    0.95
    uppet
    0.88
    erson
    0.88
    masters
    0.86
    ersen
    0.84
    ete
    0.83
    etry
    0.83
    ublic
    0.80
    asus
    0.79
    Activations Density 0.034%

    No Known Activations