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. 8-RES-JB
    6. 15257
    Prev
    Next
    INDEX
    Explanations

    mentions of large gatherings of people or crowds

    oai_token-act-pair · gpt-3.5-turbo

    instances of large gatherings or crowds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iasis
    -0.75
    deal
    -0.74
    tein
    -0.73
     patents
    -0.72
     memos
    -0.71
    framework
    -0.70
     timelines
    -0.70
    esson
    -0.69
    senal
    -0.68
    paste
    -0.67
    POSITIVE LOGITS
     cheering
    1.44
     chanting
    1.26
     spectators
    1.25
     cheers
    1.23
     cheered
    1.15
     applause
    1.11
     applaud
    1.10
     roar
    1.10
     roared
    1.09
     onlook
    1.09
    Activations Density 0.379%

    No Known Activations