© 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. 6809
    Prev
    Next
    INDEX
    Explanations

    physical activities or movements

    oai_token-act-pair · gpt-3.5-turbo

    practices related to mindfulness and physical activities

    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
    âĤ¬
    -0.82
    Europe
    -0.78
    iverse
    -0.76
    redit
    -0.75
    ropolis
    -0.73
    2016
    -0.72
    Mill
    -0.72
    endor
    -0.71
    é¾
    -0.71
    origin
    -0.71
    POSITIVE LOGITS
     kissing
    1.46
     hugging
    1.39
     gestures
    1.36
     nodding
    1.30
     brushing
    1.29
     coughing
    1.27
     chanting
    1.27
     kisses
    1.26
     licking
    1.26
     whispering
    1.25
    Activations Density 0.373%

    No Known Activations