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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 1998
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences with the word "quietly"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "quietly"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gram
    -0.66
     comparison
    -0.63
    original
    -0.62
     Degree
    -0.61
     attribution
    -0.61
     Due
    -0.60
     âĸº
    -0.59
     representation
    -0.58
     redu
    -0.58
     XX
    -0.57
    POSITIVE LOGITS
     quietly
    3.48
     silently
    2.42
     calmly
    1.92
     softly
    1.80
     peacefully
    1.67
     secretly
    1.65
     slowly
    1.60
     patiently
    1.59
     loudly
    1.58
     politely
    1.55
    Activations Density 0.011%

    No Known Activations