© 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. 23959
    Prev
    Next
    INDEX
    Explanations

    instances of the verb 'is' and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered 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
    172
    +0.09
    0.4%
    420
    +0.09
    0.4%
    588
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.09
    0.02
    304
    +0.09
    0.02
    588
    +0.09
    0.02
    Negative Logits
    ¥ŀ
    -0.63
     regenerate
    -0.61
     stakes
    -0.60
    gdala
    -0.59
    ãĥĥãĥĪ
    -0.57
     depreciation
    -0.56
     duplicate
    -0.56
     squid
    -0.55
     combustion
    -0.55
     deprived
    -0.55
    POSITIVE LOGITS
    abeth
    1.16
    quel
    1.05
    kell
    1.03
    sel
    1.01
    rael
    0.96
    soon
    0.95
    henko
    0.94
    terness
    0.94
    que
    0.94
    andra
    0.92
    Activations Density 0.033%

    No Known Activations