© 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 1536
    9. 8-RES_FS1536-JB
    11. 6
    Prev
    Next
    INDEX
    Explanations

    phrases related to opportunities and chances

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    718
    +0.12
    0.5%
    493
    +0.10
    0.5%
    506
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.12
    0.07
    247
    +0.10
    0.07
    575
    +0.10
    0.09
    Negative Logits
    hemat
    -0.81
    miah
    -0.76
    aida
    -0.72
    ometimes
    -0.71
    ashion
    -0.70
    utters
    -0.67
    cht
    -0.66
    hematic
    -0.66
    raint
    -0.65
    arling
    -0.65
    POSITIVE LOGITS
    llor
    1.13
     chance
    0.83
    finder
    0.83
     opportunity
    0.81
    chance
    0.76
     Encounter
    0.74
     Rouhani
    0.73
     afforded
    0.73
    izons
    0.72
     opportunities
    0.72
    Activations Density 1.821%

    No Known Activations