© 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. 22338
    Prev
    Next
    INDEX
    Explanations

    statements or descriptions related to learning experiences or gaining knowledge

    oai_token-act-pair · gpt-3.5-turbo

    statements about learning or lessons learned from experiences

    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
    endez
    -0.65
     backdrop
    -0.63
     è£ıè¦ļéĨĴ
    -0.62
    yip
    -0.62
    chairs
    -0.61
    pex
    -0.60
    ItemImage
    -0.60
    ecake
    -0.58
    Constructed
    -0.57
     Buckingham
    -0.57
    POSITIVE LOGITS
     lesson
    1.57
     lessons
    1.39
     valuable
    1.12
     invaluable
    1.11
     Lessons
    1.05
     tricks
    0.98
     firsthand
    0.92
     Learned
    0.91
     wisdom
    0.83
     trick
    0.83
    Activations Density 0.150%

    No Known Activations