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. 4-RES-JB
    6. 18080
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial markets and measurements, particularly focusing on market capitalization and market share

    oai_token-act-pair · gpt-3.5-turbo

    terms related to market metrics and capitalization

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

    No Comments

    Negative Logits
    ĪĴ
    -0.80
    iday
    -0.72
    azeera
    -0.72
    igo
    -0.71
     biome
    -0.70
    enary
    -0.70
     detach
    -0.65
     surg
    -0.63
     Scully
    -0.62
    inguished
    -0.61
    POSITIVE LOGITS
     Prices
    0.84
     commodity
    0.76
     CDs
    0.73
     apples
    0.72
     Auction
    0.72
     commodities
    0.72
     hamb
    0.71
    ecake
    0.70
     coupons
    0.70
    estate
    0.70
    Activations Density 0.316%

    No Known Activations