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. 17710
    Prev
    Next
    INDEX
    Explanations

    references to birthdays

    oai_token-act-pair · gpt-3.5-turbo

    words related to birthdays

    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
    force
    -0.65
     Mono
    -0.64
    ilities
    -0.64
    nell
    -0.63
    onduct
    -0.62
     adapt
    -0.62
     Weld
    -0.61
    lite
    -0.60
     force
    -0.60
    ernels
    -0.60
    POSITIVE LOGITS
     birthday
    3.87
     Birthday
    2.98
     anniversary
    1.92
     Anniversary
    1.60
    Birth
    1.46
     wedding
    1.44
    birth
    1.43
    iversary
    1.36
     birth
    1.32
     Christmas
    1.25
    Activations Density 0.011%

    No Known Activations