Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 122
    Prev
    Next
    INDEX
    Explanations

    financial and administrative terms in a text, such as "records", "credit card", "documents", "tax", "insurance", "bank account", "debt", "unemployment benefits", "hardship", "forecast", and "stock"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to housing and financial records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JM
    -0.67
    minist
    -0.65
    ensional
    -0.60
     Sutherland
    -0.59
    PLIED
    -0.54
    930
    -0.53
    udeau
    -0.52
    agonist
    -0.52
    Standard
    -0.51
    itatively
    -0.50
    POSITIVE LOGITS
     etc
    1.04
     blah
    0.66
     respectively
    0.65
     gal
    0.62
     thereof
    0.59
    etc
    0.59
     ones
    0.54
     circ
    0.52
     dancers
    0.52
     pros
    0.52
    Activations Density 0.834%

    No Known Activations