© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 5121
    Prev
    Next
    INDEX
    Explanations

    definitions of terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    definitions and variations of the word "definitely."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sth
    -0.66
    ï¸
    -0.57
     Publishers
    -0.57
     Madness
    -0.57
     fingerprints
    -0.57
     palms
    -0.56
     trunk
    -0.55
     spirit
    -0.55
     vans
    -0.54
     Horses
    -0.54
    POSITIVE LOGITS
    initions
    1.59
    initely
    1.57
    erred
    1.50
    inite
    1.43
    icient
    1.39
    endants
    1.38
    amation
    1.38
    ensive
    1.37
    eating
    1.33
    ective
    1.32
    Activations Density 0.025%

    No Known Activations