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. 2-RES-JB
    6. 16172
    Prev
    Next
    INDEX
    Explanations

    dates in the month of December

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the date "December 9"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aird
    -0.86
    Reviewer
    -0.79
    htaking
    -0.68
    SPA
    -0.65
     diaper
    -0.65
     Ital
    -0.64
    achu
    -0.63
    cher
    -0.62
    ļé
    -0.62
    JP
    -0.61
    POSITIVE LOGITS
     2015
    0.99
     2012
    0.95
     2014
    0.95
     2013
    0.95
     2018
    0.94
     2016
    0.94
     2017
    0.93
     2010
    0.91
     2011
    0.91
    EMBER
    0.90
    Activations Density 0.017%

    No Known Activations