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. 10-RES-JB
    6. 21923
    Prev
    Next
    INDEX
    Explanations

    events or occasions worth celebrating

    oai_token-act-pair · gpt-3.5-turbo

    references to celebrations and significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perate
    -0.78
    lycer
    -0.76
     panicked
    -0.70
     beware
    -0.70
     contradicts
    -0.65
    pressure
    -0.65
    cler
    -0.64
    room
    -0.64
    itute
    -0.63
    amina
    -0.63
    POSITIVE LOGITS
     anniversary
    1.66
     birthday
    1.41
     Anniversary
    1.26
     milestone
    1.26
    iversary
    1.17
     milestones
    1.16
     Birthday
    1.14
     accomplishments
    1.13
     achievements
    1.12
     occasion
    1.06
    Activations Density 0.211%

    No Known Activations