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. 11-RES-JB
    6. 19637
    Prev
    Next
    INDEX
    Explanations

    large amounts of money, such as billions and millions, usually related to financial transactions or revenue

    oai_token-act-pair · gpt-3.5-turbo

    references to large sums of money or financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cknow
    -0.77
     Niet
    -0.63
    ãĥ¤
    -0.59
    idth
    -0.57
    ©¶æ
    -0.56
     confir
    -0.54
     Collider
    -0.53
    arton
    -0.52
    aple
    -0.52
    anwhile
    -0.52
    POSITIVE LOGITS
     worth
    1.25
     dollars
    1.10
     (£
    1.08
     USD
    0.92
    worth
    0.91
     of
    0.88
     ($
    0.86
     in
    0.86
     owed
    0.85
     annually
    0.83
    Activations Density 0.104%

    No Known Activations