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. 7-RES-JB
    6. 9227
    Prev
    Next
    INDEX
    Explanations

    financial terms and market-related news

    oai_token-act-pair · gpt-3.5-turbo

    references to financial markets and economic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indoctr
    -0.94
     ACLU
    -0.85
     tresp
    -0.84
     rapist
    -0.80
     inmates
    -0.79
     queer
    -0.76
     LGBTQ
    -0.76
     pedoph
    -0.76
     genders
    -0.76
     canon
    -0.75
    POSITIVE LOGITS
     bullish
    1.46
     forecast
    1.25
     forecasting
    1.21
     forecasts
    1.20
    NYSE
    1.17
     liquidity
    1.12
    Shares
    1.08
     OPEC
    1.08
     volatility
    1.05
    flation
    1.04
    Activations Density 1.263%

    No Known Activations