© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 4076
    Prev
    Next
    INDEX
    Explanations

    information related to events and gatherings

    oai_token-act-pair · gpt-3.5-turbo

    events or celebrations related to community activities and gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.92
    itably
    -0.79
    lying
    -0.77
    onyms
    -0.75
    ername
    -0.75
     narrower
    -0.74
    iologist
    -0.74
     pores
    -0.72
     griev
    -0.72
    sheets
    -0.72
    POSITIVE LOGITS
     Celebration
    1.47
     Festival
    1.46
     Dinner
    1.34
     Tournament
    1.34
     festivities
    1.34
     event
    1.31
     Contest
    1.28
     Parade
    1.28
     Marathon
    1.27
     Championships
    1.27
    Activations Density 0.231%

    No Known Activations