© 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. 0-RES-JB
    11. 11280
    Prev
    Next
    INDEX
    Explanations

    mentions of events or ceremonies related to weddings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "wedding" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chomsky
    -0.97
     Blocks
    -0.74
    rates
    -0.70
     Incre
    -0.70
    SR
    -0.70
     Stim
    -0.68
    redit
    -0.67
    Pac
    -0.65
     substant
    -0.65
    ernels
    -0.65
    POSITIVE LOGITS
     wedding
    3.61
     weddings
    3.03
     Wedding
    3.01
     bride
    2.10
     marriage
    1.90
     funeral
    1.74
     Marriage
    1.66
     Bride
    1.64
     marriages
    1.60
     birthday
    1.52
    Activations Density 0.014%

    No Known Activations