© 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. 11-RES-JB
    11. 20400
    Prev
    Next
    INDEX
    Explanations

    formal statements of certainty or confidence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.68
    bread
    -0.62
    %%%%
    -0.62
     Tycoon
    -0.58
     Goodbye
    -0.57
     ILCS
    -0.57
     Defeat
    -0.57
     goodbye
    -0.56
     Stability
    -0.56
    ¢
    -0.56
    POSITIVE LOGITS
     intrigued
    1.44
     pleasantly
    1.40
     amazed
    1.29
     impressed
    1.26
     curious
    1.25
     delighted
    1.25
     fascinated
    1.24
     thrilled
    1.24
     inspired
    1.23
     surprised
    1.23
    Activations Density 0.166%

    No Known Activations