© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 45515
    Prev
    Next
    INDEX
    Explanations

    phrases that contain forms of the word "of."

    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
    150
    +0.13
    0.6%
    170
    +0.11
    0.5%
    53
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.13
    0.03
    150
    +0.11
    0.02
    103
    +0.10
    0.02
    Negative Logits
    DragonMagazine
    -0.90
    ibling
    -0.83
    orie
    -0.83
    fully
    -0.76
    oresc
    -0.74
     contrace
    -0.74
     restrooms
    -0.71
    binary
    -0.69
    ERAL
    -0.65
    iov
    -0.65
    POSITIVE LOGITS
    Saint
    0.84
     authenticity
    0.75
     Success
    0.75
     truce
    0.75
     secrecy
    0.74
     gratitude
    0.70
     Rebirth
    0.70
     saints
    0.68
     regeneration
    0.67
     affirmation
    0.66
    Activations Density 0.030%

    No Known Activations