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. 22070
    Prev
    Next
    INDEX
    Explanations

    references to specific days of the week

    oai_token-act-pair · gpt-3.5-turbo

    references to the days of the week, particularly Friday

    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
     Minotaur
    -0.76
     dumb
    -0.63
     Hydra
    -0.62
     Calculator
    -0.62
     Cerberus
    -0.61
     Liquid
    -0.61
     Titans
    -0.61
     Capital
    -0.60
     enlarge
    -0.60
     Unicorn
    -0.60
    POSITIVE LOGITS
    iday
    5.07
    idays
    1.66
    aday
    1.37
    eday
    1.31
    umn
    1.17
    ursday
    1.07
    oday
    1.05
    nesday
    1.04
    ideo
    1.01
    onday
    0.99
    Activations Density 0.010%

    No Known Activations