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. 12-RES-JB
    6. 14595
    Prev
    Next
    INDEX
    Explanations

    terms related to problems or challenges in different fields, such as healthcare, economics, and land management

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    topics related to ecological and environmental impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymm
    -0.78
     Canaver
    -0.64
     Changed
    -0.62
     reformed
    -0.61
     architects
    -0.60
    cients
    -0.59
     Observer
    -0.58
    gans
    -0.57
     redesigned
    -0.56
    changed
    -0.56
    POSITIVE LOGITS
     costs
    1.05
     density
    1.04
     rates
    1.03
     count
    1.01
     burden
    0.99
    ensity
    0.99
     counts
    0.98
     burdens
    0.97
     prices
    0.94
     turnover
    0.92
    Activations Density 0.342%

    No Known Activations