© 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. 1-RES-JB
    6. 11475
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in '-ingly'

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that indicate a degree of intensity or manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    docs
    -0.82
    emaker
    -0.69
    href
    -0.67
     Greenwich
    -0.65
    rieving
    -0.65
     Must
    -0.60
    ains
    -0.60
    ials
    -0.59
     Gazette
    -0.59
     attendees
    -0.57
    POSITIVE LOGITS
    ingly
    1.19
    theless
    1.02
    etheless
    0.95
    NESS
    0.88
    nesses
    0.87
     unden
    0.74
    BuyableInstoreAndOnline
    0.74
    clad
    0.72
    lihood
    0.71
    entimes
    0.71
    Activations Density 0.007%

    No Known Activations