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. 11595
    Prev
    Next
    INDEX
    Explanations

    references to financial or business-related terms, specifically related to ownership and investments such as equity, partners, and investors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to equity in financial contexts

    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
    slow
    -0.76
    achu
    -0.73
    abouts
    -0.73
    sonian
    -0.72
    STON
    -0.70
    Ø©
    -0.69
    ================================================================
    -0.69
    FACE
    -0.69
     Daylight
    -0.67
    Ïī
    -0.66
    POSITIVE LOGITS
     securities
    1.01
     crowdfunding
    0.98
     stakes
    0.94
     investor
    0.92
     investors
    0.92
     Investor
    0.89
     investments
    0.88
     Investors
    0.85
     Securities
    0.84
     holdings
    0.84
    Activations Density 0.043%

    No Known Activations