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. 10-RES-JB
    6. 13028
    Prev
    Next
    INDEX
    Explanations

    terms related to different types of products or economic instruments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various societal and financial 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
    epad
    -0.87
    »Ĵ
    -0.85
    estamp
    -0.83
    icum
    -0.82
    20439
    -0.76
    romeda
    -0.76
     Marketable
    -0.75
    externalActionCode
    -0.75
    auga
    -0.74
    ighthouse
    -0.74
    POSITIVE LOGITS
     owners
    1.20
     makers
    1.17
     manufacturers
    1.11
     holders
    1.09
     registrations
    1.06
     operators
    1.04
     rentals
    1.03
     enthusiasts
    1.01
    holders
    1.01
     usage
    1.00
    Activations Density 0.385%

    No Known Activations