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. 22023
    Prev
    Next
    INDEX
    Explanations

    mentions of celebrations or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "celebration."

    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
    opt
    -0.69
    ilk
    -0.69
     unreliable
    -0.64
    Agent
    -0.62
    els
    -0.62
    erman
    -0.61
    gray
    -0.61
     lik
    -0.61
    ernels
    -0.61
    Plug
    -0.60
    POSITIVE LOGITS
     celebration
    3.72
     celebrations
    3.03
     Celebration
    2.65
     celebrating
    2.20
     celebr
    2.14
     commem
    2.14
     festivities
    2.11
     celebrate
    2.09
     Celebr
    1.80
     ceremony
    1.75
    Activations Density 0.027%

    No Known Activations