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. 11669
    Prev
    Next
    INDEX
    Explanations

    onset/transition words indicating movement or transfer

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "onto" and its variations throughout the text

    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
    coord
    -0.64
    len
    -0.64
    gans
    -0.63
    lege
    -0.61
    gran
    -0.59
    ellig
    -0.58
    lesiastical
    -0.57
    erate
    -0.57
    tx
    -0.56
    few
    -0.56
    POSITIVE LOGITS
    pload
    1.05
     behalf
    0.84
    chnology
    0.83
    creen
    0.80
     onto
    0.79
    itored
    0.76
     shelves
    0.75
    coming
    0.74
    apons
    0.74
    kefeller
    0.73
    Activations Density 0.008%

    No Known Activations