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. 0-RES-JB
    6. 5961
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial investments

    oai_token-act-pair · gpt-3.5-turbo

    references to investments and related financial terms

    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
     infect
    -0.87
     silence
    -0.84
     deaf
    -0.80
     disabling
    -0.75
     subs
    -0.74
     disgust
    -0.74
     blister
    -0.74
     cel
    -0.73
     voc
    -0.72
     hers
    -0.72
    POSITIVE LOGITS
     Investment
    3.40
     Investments
    2.46
     Investors
    1.86
     Asset
    1.77
     Investor
    1.70
     Securities
    1.65
     Banking
    1.64
     Advis
    1.61
     Trading
    1.54
     Financial
    1.52
    Activations Density 0.030%

    No Known Activations