Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19866
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of camping activities and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to camping and related 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
     quot
    -0.70
     Commonwealth
    -0.60
     Tsukuyomi
    -0.58
    lihood
    -0.58
     Synd
    -0.56
     knot
    -0.56
     Thief
    -0.56
    piring
    -0.55
     wise
    -0.54
     republic
    -0.54
    POSITIVE LOGITS
    grounds
    1.56
    ground
    1.55
    fires
    1.38
    fire
    1.25
    agna
    1.20
    agne
    1.13
    sites
    1.01
    camp
    1.00
    anas
    0.99
    yrinth
    0.98
    Activations Density 0.042%

    No Known Activations