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. 6-RES-JB
    6. 1998
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and research methodologies

    oai_token-act-pair · gpt-3.5-turbo

    information related to scientific studies and research methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flats
    -0.67
     rooft
    -0.66
     upstairs
    -0.66
     belt
    -0.65
     lett
    -0.64
     miles
    -0.64
     renting
    -0.64
     bunker
    -0.63
     Greg
    -0.62
     legally
    -0.62
    POSITIVE LOGITS
    Introduction
    1.09
    Acknowled
    1.08
    Discussion
    1.05
    References
    1.05
    RESULTS
    1.04
    Overview
    0.99
    TABLE
    0.96
    FIG
    0.94
    Abstract
    0.94
    Summary
    0.94
    Activations Density 0.304%

    No Known Activations