Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 45507
    Prev
    Next
    INDEX
    Explanations

    references to Buddhism and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    481
    +0.14
    0.6%
    343
    +0.12
    0.6%
    52
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.14
    0.01
    288
    +0.12
    0.01
    48
    +0.11
    0.01
    Negative Logits
    ted
    -0.76
    ochond
    -0.74
    */(
    -0.73
    ppard
    -0.71
    igate
    -0.70
     Luthor
    -0.70
    UV
    -0.70
    vous
    -0.68
    BER
    -0.68
    vable
    -0.68
    POSITIVE LOGITS
     monks
    1.07
     monk
    0.93
     Buddhist
    0.88
     temple
    0.83
     teachings
    0.83
     precept
    0.81
     Buddhism
    0.80
     meditation
    0.79
     temples
    0.78
     Dharma
    0.78
    Activations Density 0.012%

    No Known Activations