© 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. 45700
    Prev
    Next
    INDEX
    Explanations

    complete sentences or statements that convey definitive information

    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
    +0.14
    0.7%
    6
    +0.12
    0.5%
    640
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.14
    0.12
    679
    +0.12
    0.10
    454
    +0.12
    0.09
    Negative Logits
     extinct
    -0.88
     affili
    -0.80
     cryptoc
    -0.78
     selfie
    -0.77
     farmland
    -0.77
     unstoppable
    -0.75
     tyr
    -0.73
     aspire
    -0.72
     affordable
    -0.71
     favourite
    -0.71
    POSITIVE LOGITS
     Moreover
    1.42
     Nevertheless
    1.42
     Nonetheless
    1.40
     Presumably
    1.36
     Furthermore
    1.34
     Consequently
    1.33
     Similarly
    1.27
     Therefore
    1.27
     Likewise
    1.26
     However
    1.25
    Activations Density 0.371%

    No Known Activations