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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 15964
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal events or occasions

    oai_token-act-pair · gpt-3.5-turbo

    references to formal events or gatherings

    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
    tested
    -0.68
    izons
    -0.67
    independent
    -0.67
    Len
    -0.66
    Feed
    -0.63
     extrap
    -0.62
    Agg
    -0.60
    bass
    -0.59
    ilk
    -0.59
    aspers
    -0.59
    POSITIVE LOGITS
     ceremony
    3.97
     ceremonies
    3.11
     ceremonial
    1.70
     ceremon
    1.68
     Cere
    1.68
     ritual
    1.61
     rite
    1.60
     celebration
    1.60
     festivities
    1.59
     rites
    1.57
    Activations Density 0.021%

    No Known Activations