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. 9-RES-JB
    6. 18676
    Prev
    Next
    INDEX
    Explanations

    references to fundraising and financial goals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fundraising goals and financial achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ictionary
    -0.82
    £ı
    -0.80
    orgetown
    -0.79
    foreign
    -0.77
    unction
    -0.77
     eaves
    -0.75
    aspers
    -0.74
    dayName
    -0.73
    gregation
    -0.72
     aph
    -0.72
    POSITIVE LOGITS
     Kickstarter
    1.68
     backers
    1.48
     backer
    1.39
     Funding
    1.36
     crowdfunding
    1.35
     Patreon
    1.32
     Stretch
    1.26
    Stretch
    1.23
     pledges
    1.23
    funding
    1.21
    Activations Density 0.739%

    No Known Activations