© 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. 0-RES-JB
    11. 4832
    Prev
    Next
    INDEX
    Explanations

    adjectives related to the concept of overwhelming

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotions or feelings of being overwhelmed

    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
     Correction
    -0.67
     ©
    -0.67
    idian
    -0.67
    rake
    -0.66
    SHIP
    -0.65
     Pen
    -0.62
    lin
    -0.61
    pta
    -0.61
    eret
    -0.60
    jar
    -0.60
    POSITIVE LOGITS
     overwhelming
    3.67
     overpower
    1.79
     overwhelmingly
    1.77
     overwhelm
    1.66
     daunting
    1.54
     intimidating
    1.43
     overwhelmed
    1.42
     overriding
    1.41
     vast
    1.37
     irresistible
    1.33
    Activations Density 0.016%

    No Known Activations