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. 0-RES-JB
    6. 14618
    Prev
    Next
    INDEX
    Explanations

    words related to hovering or floating above something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to user interface interactions, specifically hover effects in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eyes
    -0.80
    sson
    -0.75
    raid
    -0.71
    emale
    -0.68
    Tel
    -0.68
     seq
    -0.67
    Tan
    -0.66
    atta
    -0.66
    assad
    -0.66
    alties
    -0.65
    POSITIVE LOGITS
     hover
    2.23
     Hover
    1.67
     hovering
    1.65
    function
    1.50
    esame
    1.43
    idget
    1.39
    hover
    1.23
     malfunction
    1.11
     jQuery
    1.02
     Elm
    0.98
    Activations Density 0.061%

    No Known Activations