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

    Neuronpedia

    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. 0-RES-JB
    11. 5401
    Prev
    Next
    INDEX
    Explanations

    phrases related to stocks or stock-related terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to stock market terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fey
    -0.81
     guid
    -0.69
     transl
    -0.65
     advers
    -0.62
     Franc
    -0.62
     aura
    -0.62
     translator
    -0.60
     directives
    -0.59
     cu
    -0.59
     overt
    -0.59
    POSITIVE LOGITS
    stock
    4.89
    stocks
    3.48
    Stock
    2.49
     stock
    1.96
     Stock
    1.80
     stocks
    1.54
    crop
    1.10
    street
    1.07
    bush
    1.04
    share
    1.03
    Activations Density 0.013%

    No Known Activations