© 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. 25788
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a specific action or sentiment, often related to personal experiences or opinions

    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
    352
    +0.13
    0.6%
    575
    +0.12
    0.5%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.13
    0.14
    103
    +0.12
    0.11
    23
    +0.10
    0.11
    Negative Logits
     Glou
    -0.68
    anwhile
    -0.68
     Ambro
    -0.67
     Skydragon
    -0.65
     Thomson
    -0.65
     Sleeping
    -0.64
     Bened
    -0.63
     Ket
    -0.62
     incent
    -0.62
     Simpl
    -0.61
    POSITIVE LOGITS
    ¬
    1.29
    Ĵ
    1.15
    ħ
    1.11
    ĸ
    1.10
    ı
    1.10
    į
    1.08
    Ļ
    1.06
    Ķ
    1.04
    ¯
    1.03
    ĩ
    1.02
    Activations Density 0.223%

    No Known Activations