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. 5852
    Prev
    Next
    INDEX
    Explanations

    references to changes or trends in prices, especially relating to economic conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to prices and their fluctuations in the context of economic discussions

    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
    eworks
    -0.99
    orough
    -0.85
    irlf
    -0.84
    blance
    -0.83
    mbuds
    -0.80
    enegger
    -0.79
    andestine
    -0.78
    swer
    -0.78
    aug
    -0.78
    estern
    -0.76
    POSITIVE LOGITS
     gou
    1.10
     inflation
    1.01
     volatility
    0.99
     prices
    0.98
     fluctuations
    0.97
     premiums
    0.94
     fluct
    0.92
     deflation
    0.91
     price
    0.86
     indices
    0.84
    Activations Density 0.041%

    No Known Activations