© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 2223
    Prev
    Next
    INDEX
    Explanations

    phrases related to punctuation, specifically the period or semicolon as the highest activation values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of punctuation marks, particularly periods and semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    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

    Negative Logits
     emanc
    -0.81
     glim
    -0.79
     involuntary
    -0.77
     tyr
    -0.74
     overdose
    -0.73
     drift
    -0.73
     rall
    -0.71
     induction
    -0.71
     emission
    -0.70
     timet
    -0.70
    POSITIVE LOGITS
     Therefore
    1.27
     Accordingly
    1.24
     Hence
    1.24
     Thus
    1.22
     Moreover
    1.22
     Additionally
    1.22
     However
    1.22
     Regardless
    1.20
     Furthermore
    1.19
     Likewise
    1.19
    Activations Density 0.604%

    No Known Activations