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. 1-RES-JB
    6. 9808
    Prev
    Next
    INDEX
    Explanations

    words related to "Touch" technology, specifically focusing on terms related to features, design elements, and functionalities

    oai_token-act-pair · gpt-3.5-turbo

    references to "Touch" technology, particularly related to Apple's products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    swick
    -0.80
    adiator
    -0.69
    ais
    -0.68
    committee
    -0.67
     sidx
    -0.66
     lodging
    -0.65
    abwe
    -0.64
    addafi
    -0.64
     cruc
    -0.63
    ammed
    -0.62
    POSITIVE LOGITS
     Touch
    1.12
    stones
    1.03
    stone
    0.94
    Touch
    0.90
    downs
    0.87
    Tap
    0.86
    backs
    0.86
    Arcade
    0.84
     Hands
    0.79
    back
    0.75
    Activations Density 0.011%

    No Known Activations