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. 18956
    Prev
    Next
    INDEX
    Explanations

    monetary amounts expressed in millions or billions

    oai_token-act-pair · gpt-3.5-turbo

    monetary values or financial figures

    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
     Ging
    -0.62
     Wid
    -0.62
     Bleach
    -0.59
    ItemThumbnailImage
    -0.59
     Anaheim
    -0.57
    girls
    -0.57
     âĵĺ
    -0.57
    igators
    -0.56
    deen
    -0.56
    oké
    -0.54
    POSITIVE LOGITS
     billion
    1.23
     million
    1.20
    -$
    1.12
    billion
    1.10
    00
    1.08
    million
    1.06
     Billion
    1.01
     trillion
    0.96
     MILL
    0.95
    bn
    0.93
    Activations Density 0.099%

    No Known Activations