© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 24007
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" to indicate emphasis or connection in sentences

    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
    679
    +0.13
    0.6%
    393
    +0.12
    0.6%
    150
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.13
    0.04
    551
    +0.12
    0.04
    150
    +0.10
    0.03
    Negative Logits
    Returns
    -0.77
    quet
    -0.73
    roth
    -0.69
    \\\\\\\\
    -0.68
    LY
    -0.67
    Ble
    -0.64
    Desk
    -0.62
    Fax
    -0.61
    EMBER
    -0.61
    ival
    -0.60
    POSITIVE LOGITS
     comprise
    1.24
     surround
    1.12
     populate
    1.09
     constitute
    1.03
     inhabit
    1.00
     mattered
    1.00
     compose
    0.99
     plague
    0.97
     are
    0.93
     were
    0.92
    Activations Density 0.080%

    No Known Activations