© 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 24576
    5. 8-RES_FS24576-JB
    6. 1830
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns indicating relationships

    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
    92
    +0.13
    0.6%
    362
    +0.13
    0.6%
    393
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.04
    92
    +0.13
    0.03
    562
    +0.10
    0.03
    Negative Logits
    sburg
    -0.75
    quez
    -0.69
    ocument
    -0.67
    bender
    -0.66
    ORPG
    -0.66
    redits
    -0.63
    Reilly
    -0.63
    ANCE
    -0.62
    CHAPTER
    -0.62
     Recomm
    -0.61
    POSITIVE LOGITS
     own
    1.27
     fists
    1.07
     utmost
    1.06
     newfound
    1.04
     usual
    0.97
     sights
    0.93
     friends
    0.93
     eyes
    0.92
     buddies
    0.90
     knees
    0.90
    Activations Density 0.087%

    No Known Activations