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. 0-RES-JB
    6. 22983
    Prev
    Next
    INDEX
    Explanations

    words related to festivals or events

    oai_token-act-pair · gpt-3.5-turbo

    references to festivals and events

    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
     guidance
    -0.69
     immediate
    -0.69
     navig
    -0.69
     intervening
    -0.67
     traced
    -0.66
     monitor
    -0.65
     presumed
    -0.63
     steps
    -0.63
     liabilities
    -0.61
     trillion
    -0.60
    POSITIVE LOGITS
    fest
    4.29
    Fest
    2.73
     fest
    2.35
     Fest
    2.18
     Festival
    1.29
     festivals
    1.23
     festival
    1.22
    athon
    1.01
     Celebration
    1.00
    furt
    0.99
    Activations Density 0.015%

    No Known Activations