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. 19695
    Prev
    Next
    INDEX
    Explanations

    keywords related to fundraising and financial matters, such as "fund," "raising," "investment," and "donations."

    oai_token-act-pair · gpt-3.5-turbo

    references to funding or financial support related to various activities or organizations

    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
     Wand
    -0.69
     Coil
    -0.68
    èª
    -0.68
     vinegar
    -0.67
     Haz
    -0.65
     Nieto
    -0.65
     discont
    -0.65
     indign
    -0.64
     Ange
    -0.63
     tem
    -0.63
    POSITIVE LOGITS
    raising
    1.47
    ament
    1.34
    amental
    1.23
    aments
    0.99
    fund
    0.98
    rolled
    0.96
    folio
    0.96
    funded
    0.95
    ers
    0.94
    acion
    0.93
    Activations Density 0.041%

    No Known Activations