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. 12-RES-JB
    6. 14699
    Prev
    Next
    INDEX
    Explanations

    financial terms and entities related to business filings and governance issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to financial regulatory bodies and securities exchanges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    kinson
    -0.67
     fart
    -0.64
    fu
    -0.63
    oÄŁ
    -0.60
    ouf
    -0.60
    andowski
    -0.59
    wav
    -0.59
    packs
    -0.59
    ontent
    -0.57
    âĻ¥
    -0.57
    POSITIVE LOGITS
     Exchange
    1.12
     Commission
    0.91
     Examination
    0.89
     regulator
    0.87
     Markets
    0.83
     regulators
    0.81
     Lit
    0.80
     SEC
    0.80
     Regulatory
    0.79
     Registration
    0.79
    Activations Density 0.068%

    No Known Activations