© 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. 6-RES-JB
    11. 13464
    Prev
    Next
    INDEX
    Explanations

    words ending in "-ly"

    oai_token-act-pair · gpt-3.5-turbo

    adverbs, particularly those that end in "ly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilater
    -0.99
    bucks
    -0.79
    pie
    -0.77
    eers
    -0.77
    irtual
    -0.66
    arella
    -0.64
    ulu
    -0.64
    afety
    -0.64
     Weiner
    -0.64
    irlf
    -0.63
    POSITIVE LOGITS
     speaking
    0.83
     Sabha
    0.77
     Speaking
    0.77
     RELE
    0.70
    entimes
    0.70
    tics
    0.69
    theless
    0.67
    UTERS
    0.67
     sourced
    0.67
    \\\\
    0.65
    Activations Density 0.037%

    No Known Activations