© 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. 45777
    Prev
    Next
    INDEX
    Explanations

    the word "been."

    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
    +0.17
    0.8%
    566
    +0.14
    0.6%
    102
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.17
    0.03
    566
    +0.14
    0.03
    102
    +0.12
    0.03
    Negative Logits
    rouse
    -0.77
    âĨij
    -0.68
    ierrez
    -0.67
    Nich
    -0.67
    inks
    -0.64
     Brach
    -0.64
    æ©
    -0.63
    Yan
    -0.63
     Replacement
    -0.63
     Higgins
    -0.62
    POSITIVE LOGITS
    cffffcc
    0.92
     released
    0.88
     replaced
    0.87
     deprecated
    0.86
     updated
    0.85
     hijacked
    0.82
     indicted
    0.82
     awhile
    0.82
     upgraded
    0.81
     moved
    0.81
    Activations Density 0.045%

    No Known Activations