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. 11-RES-JB
    6. 10969
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to research and development, as well as references to people or organizations working together towards a common goal

    oai_token-act-pair · gpt-3.5-turbo

    references to various communities and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     RELEASE
    -0.69
     Picks
    -0.63
     Skydragon
    -0.62
    ãĤ´ãĥ³
    -0.62
    inventoryQuantity
    -0.61
    luster
    -0.59
     resolves
    -0.58
     Deter
    -0.58
    Benz
    -0.57
     Received
    -0.57
    POSITIVE LOGITS
     lurking
    1.09
     unaccount
    0.97
     waiting
    0.97
     available
    0.96
     floating
    0.96
     circulating
    0.95
     out
    0.93
     roaming
    0.90
     scattered
    0.90
     everywhere
    0.90
    Activations Density 0.292%

    No Known Activations