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. 8-RES-JB
    6. 21406
    Prev
    Next
    INDEX
    Explanations

    documents or written information, especially related to official or legal matters

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of documents and related information in a context of legality or oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ggles
    -0.66
    oneliness
    -0.65
    issance
    -0.62
    aughs
    -0.62
    swer
    -0.59
     Carnage
    -0.57
     swall
    -0.57
    tarians
    -0.55
    IFE
    -0.54
    erenn
    -0.53
    POSITIVE LOGITS
     relating
    1.07
     pertaining
    1.03
     thereof
    0.91
     associated
    0.90
     totaling
    0.84
     related
    0.83
     belonging
    0.83
     necessary
    0.82
    heet
    0.79
     pertinent
    0.78
    Activations Density 0.420%

    No Known Activations