© 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. 10-RES-JB
    11. 13891
    Prev
    Next
    INDEX
    Explanations

    keywords related to economic and financial topics

    oai_token-act-pair · gpt-3.5-turbo

    key concepts and terms related to economic and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )=(
    -0.67
    hots
    -0.63
    olia
    -0.62
    ertodd
    -0.61
    imon
    -0.61
     Edited
    -0.59
    utics
    -0.59
    haps
    -0.58
    dain
    -0.58
    ,,,,
    -0.57
    POSITIVE LOGITS
     portion
    1.18
     equivalent
    0.91
     process
    0.87
     component
    0.87
    iest
    0.86
     moniker
    0.86
     aspect
    0.85
     version
    0.83
     economy
    0.82
     sector
    0.82
    Activations Density 0.739%

    No Known Activations