© 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. 19451
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of reason or belief

    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
    718
    +0.16
    0.8%
    608
    +0.15
    0.7%
    150
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.16
    0.03
    608
    +0.15
    0.03
    665
    +0.12
    0.03
    Negative Logits
     Appears
    -0.72
    ologies
    -0.67
    quickShipAvailable
    -0.66
     Laksh
    -0.65
    lip
    -0.64
    ches
    -0.64
    thumbnails
    -0.64
    soever
    -0.64
    OLOGY
    -0.63
    lets
    -0.61
    POSITIVE LOGITS
     believe
    1.07
     revisit
    1.06
     doubt
    1.01
     celebrate
    1.00
     mistrust
    0.98
     distrust
    0.96
     rejoice
    0.95
     consider
    0.92
     disbel
    0.92
     pause
    0.91
    Activations Density 0.056%

    No Known Activations