© 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. 10-RES-JB
    11. 2318
    Prev
    Next
    INDEX
    Explanations

    contractions and informal speech patterns like "I'll" or "can't."

    oai_token-act-pair · gpt-3.5-turbo

    conversational phrases that indicate personal opinions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĢij
    -0.79
    è¦ļéĨĴ
    -0.72
    âĦ¢:
    -0.70
    âĹı
    -0.70
    ¥ŀ
    -0.66
     urgently
    -0.65
    currently
    -0.64
     ®
    -0.64
     Passage
    -0.63
    ä¸Ĭ
    -0.62
    POSITIVE LOGITS
     hindsight
    1.06
    laughs
    1.01
    Laughs
    0.91
     somebody
    0.84
     [
    0.84
    .")
    0.83
     regrets
    0.80
     embarrassed
    0.79
    .'"
    0.79
     ['
    0.78
    Activations Density 0.557%

    No Known Activations