© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 19634
    Prev
    Next
    INDEX
    Explanations

    financial terms and keywords related to investing

    oai_token-act-pair · gpt-3.5-turbo

    language related to investing strategies and market behavior

    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
     Transgender
    -0.86
    Ùĩ
    -0.76
    english
    -0.76
    female
    -0.72
    Hom
    -0.71
     deport
    -0.71
    Female
    -0.71
    gender
    -0.71
    rika
    -0.70
     transgender
    -0.70
    POSITIVE LOGITS
     bullish
    1.56
     liquidity
    1.54
     IPO
    1.49
    iquid
    1.48
     investors
    1.45
     valuation
    1.44
     investor
    1.40
     hedge
    1.37
     investing
    1.37
    stocks
    1.36
    Activations Density 0.973%

    No Known Activations