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. 10-RES-JB
    6. 17600
    Prev
    Next
    INDEX
    Explanations

    words relating to the abbreviation "Sc" followed by a variety of different words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the letters 'Sc' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lapse
    -0.66
     thumbs
    -0.66
     laure
    -0.65
     wink
    -0.65
     wholesale
    -0.64
     diplom
    -0.63
     lingering
    -0.62
     remembrance
    -0.62
    etheless
    -0.61
     goodbye
    -0.60
    POSITIVE LOGITS
    ulpt
    1.57
    ratch
    1.47
    enario
    1.35
    arcity
    1.28
    issors
    1.27
    hematic
    1.26
    reenshots
    1.23
    reenshot
    1.23
    ripp
    1.23
    attered
    1.23
    Activations Density 0.014%

    No Known Activations