© 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. 14450
    Prev
    Next
    INDEX
    Explanations

    `"responding"` as a term of reaction or reply in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "responding."

    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
    ample
    -0.74
    hee
    -0.72
    umbo
    -0.71
    chin
    -0.70
    asso
    -0.67
    ogun
    -0.65
     damn
    -0.65
     kicker
    -0.65
    ogo
    -0.63
     Eclipse
    -0.63
    POSITIVE LOGITS
    TPPStreamerBot
    0.95
    BuyableInstoreAndOnline
    0.90
    DragonMagazine
    0.87
    onding
    0.83
    CLASSIFIED
    0.82
    forth
    0.80
     Tiff
    0.79
    SPONSORED
    0.76
     challeng
    0.73
     Fiona
    0.72
    Activations Density 0.037%

    No Known Activations