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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18782
    Prev
    Next
    INDEX
    Explanations

    mentions of Apple in various contexts, including legal issues and product developments

    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
    167
    +0.12
    0.5%
    343
    +0.11
    0.5%
    658
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.12
    0.03
    343
    +0.11
    0.03
    658
    +0.11
    0.03
    Negative Logits
    ovych
    -0.81
    hov
    -0.79
    egal
    -0.71
     Worcester
    -0.70
     Bucs
    -0.68
    tml
    -0.68
    yrinth
    -0.67
     Vaugh
    -0.65
     Adin
    -0.63
    selection
    -0.63
    POSITIVE LOGITS
    Ins
    1.07
    baum
    0.98
    Care
    0.93
    bee
    0.93
    jack
    0.91
    bees
    0.89
     Stores
    0.80
    Rum
    0.80
     Watch
    0.78
    Sales
    0.78
    Activations Density 0.018%

    No Known Activations