© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 8571
    Prev
    Next
    INDEX
    Explanations

    large text that prompts to enlarge or toggle

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Enlarge" in different contexts throughout the text

    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
     avail
    -0.61
    population
    -0.61
    handedly
    -0.61
     sucker
    -0.60
    ually
    -0.60
    esan
    -0.60
    lord
    -0.59
    angering
    -0.59
     neglect
    -0.58
     upt
    -0.58
    POSITIVE LOGITS
     Image
    0.95
     WATCHED
    0.88
    ONSORED
    0.87
    Enlarge
    0.87
    UTERS
    0.80
     Photo
    0.79
    ertodd
    0.72
     PHOTO
    0.70
     NPR
    0.70
     Cosponsors
    0.69
    Activations Density 0.016%

    No Known Activations