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. 17920
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms

    oai_token-act-pair · gpt-3.5-turbo

    financial terminology related to market trends and stock performance

    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
     oath
    -0.92
     indoctr
    -0.83
    authent
    -0.79
     parole
    -0.73
     lawy
    -0.73
     tattoos
    -0.72
     rabb
    -0.70
     surg
    -0.70
     trespass
    -0.70
     outlaw
    -0.69
    POSITIVE LOGITS
    flation
    1.10
     GDP
    0.98
     Ratings
    0.89
    ftime
    0.89
     Recession
    0.88
     Commerce
    0.87
     recession
    0.86
    Consumer
    0.86
    alyst
    0.85
     Moody
    0.85
    Activations Density 0.830%

    No Known Activations