© 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. 1-RES-JB
    11. 14584
    Prev
    Next
    INDEX
    Explanations

    descriptive terms indicating a sense of laziness or carefree attitude

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sleazy."

    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
    eous
    -0.74
    interrupted
    -0.72
    uates
    -0.69
    iop
    -0.66
    doms
    -0.66
    iates
    -0.65
    ipolar
    -0.64
    erto
    -0.63
    entity
    -0.63
    66666666
    -0.63
    POSITIVE LOGITS
     sle
    1.29
    azy
    0.98
     Sle
    0.82
    ight
    0.82
    pload
    0.80
    lla
    0.75
    uth
    0.75
     Sunny
    0.74
    eker
    0.74
    iness
    0.74
    Activations Density 0.004%

    No Known Activations