© 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. 26711
    Prev
    Next
    INDEX
    Explanations

    instances of the word "said" or its variations in dialogue or reporting contexts

    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
    337
    +0.10
    0.4%
    495
    +0.10
    0.4%
    238
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.10
    0.05
    337
    +0.10
    0.05
    766
    +0.09
    0.05
    Negative Logits
    ãĥİ
    -0.77
    theless
    -0.73
     conflic
    -0.72
    paralle
    -0.68
     pend
    -0.67
    姫
    -0.67
    MU
    -0.67
    thur
    -0.66
    pend
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.64
    POSITIVE LOGITS
     sarcast
    0.94
     bluntly
    0.92
     rhet
    0.91
     referring
    0.83
     emphatically
    0.79
     diplom
    0.78
     incred
    0.74
     afterward
    0.72
     aloud
    0.71
     adding
    0.69
    Activations Density 0.087%

    No Known Activations