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. 9-RES-JB
    6. 18947
    Prev
    Next
    INDEX
    Explanations

    ceremonial events and gatherings

    oai_token-act-pair · gpt-3.5-turbo

    events or gatherings that involve a significant number of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     porous
    -0.71
    hart
    -0.70
     looph
    -0.65
    rity
    -0.64
    developed
    -0.62
    haar
    -0.61
    ilk
    -0.61
     employed
    -0.61
    lying
    -0.61
    uine
    -0.60
    POSITIVE LOGITS
     festivities
    1.42
     ceremony
    1.36
     ceremonies
    1.21
     celebration
    1.17
     event
    1.14
     festival
    1.13
     Celebration
    1.10
     parade
    1.08
     procession
    1.07
     Parade
    1.06
    Activations Density 0.355%

    No Known Activations