© 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. 15970
    Prev
    Next
    INDEX
    Explanations

    titles of books and publications

    oai_token-act-pair · gpt-3.5-turbo

    titles of books or publications

    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
     icing
    -0.74
    :[
    -0.72
     roses
    -0.71
     applause
    -0.70
     watering
    -0.67
     precincts
    -0.66
    :-
    -0.66
     alarm
    -0.66
    gallery
    -0.66
     ambul
    -0.66
    POSITIVE LOGITS
     Experience
    1.22
     Definitive
    1.18
     Learned
    1.17
     Lessons
    1.15
     Strategies
    1.15
     Story
    1.15
     Debate
    1.15
     Perspective
    1.11
     Guide
    1.11
     Illustrated
    1.11
    Activations Density 0.156%

    No Known Activations