© 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. 45867
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequency in text

    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
    267
    +0.11
    0.5%
    622
    +0.11
    0.5%
    420
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.11
    0.07
    640
    +0.11
    0.05
    255
    +0.11
    0.04
    Negative Logits
     targeted
    -0.84
     priorit
    -0.81
     proactive
    -0.81
     aggressively
    -0.81
     hasht
    -0.80
     quir
    -0.80
     transitioning
    -0.79
    omics
    -0.79
     coordinated
    -0.79
     trending
    -0.78
    POSITIVE LOGITS
     Hence
    1.52
     Thus
    1.46
     Accordingly
    1.44
     Therefore
    1.33
     Suppose
    1.33
     Consequently
    1.26
     Moreover
    1.25
     Whilst
    1.24
     Notwithstanding
    1.24
     Besides
    1.22
    Activations Density 0.172%

    No Known Activations