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. 4-RES-JB
    6. 9843
    Prev
    Next
    INDEX
    Explanations

    events or activities that are starting or beginning

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the initiation of an event or activity

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

    No Comments

    Negative Logits
    é¾įå
    -0.87
    WARE
    -0.79
    sonian
    -0.67
    enne
    -0.65
    forts
    -0.64
    worn
    -0.63
    okin
    -0.63
    fed
    -0.63
    ãĥĸ
    -0.62
    mong
    -0.62
    POSITIVE LOGITS
    uberty
    0.70
    ratulations
    0.69
     Archdemon
    0.69
    odcast
    0.67
    Interstitial
    0.66
     takeoff
    0.65
    thood
    0.65
     Doors
    0.63
    reon
    0.62
     âĸº
    0.62
    Activations Density 0.033%

    No Known Activations