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. 3-RES-JB
    6. 2725
    Prev
    Next
    INDEX
    Explanations

    mentions of various locations such as cemeteries, churches, and specific places

    oai_token-act-pair · gpt-3.5-turbo

    references to cemeteries and graveyards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.83
    ihad
    -0.73
    Const
    -0.67
    estamp
    -0.67
    ĸ
    -0.65
    bits
    -0.64
    acity
    -0.64
    lihood
    -0.64
    conom
    -0.62
     Bud
    -0.62
    POSITIVE LOGITS
     Cemetery
    1.03
     cemetery
    1.01
     graveyard
    0.99
    stones
    0.90
    emetery
    0.88
     chapel
    0.88
    conservancy
    0.81
     burying
    0.78
     landfill
    0.77
    yard
    0.77
    Activations Density 0.013%

    No Known Activations