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. 26514
    Prev
    Next
    INDEX
    Explanations

    coding terminology and discussions about programming 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
    480
    +0.34
    1.6%
    384
    +0.10
    0.5%
    447
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.34
    0.03
    384
    +0.10
    0.03
    480
    +0.09
    -0.00
    Negative Logits
    ONSORED
    -0.80
    istar
    -0.71
    iversary
    -0.69
     Janeiro
    -0.68
    California
    -0.68
    successfully
    -0.67
     McAuliffe
    -0.65
    culosis
    -0.65
    NOW
    -0.65
    owered
    -0.64
    POSITIVE LOGITS
     diction
    1.31
     verbs
    1.28
     phrases
    1.26
     symbols
    1.20
     constants
    1.18
     acron
    1.16
     descriptions
    1.14
     annotations
    1.13
     modifiers
    1.13
     suffix
    1.13
    Activations Density 0.390%

    No Known Activations