© 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. 10-RES-JB
    11. 17513
    Prev
    Next
    INDEX
    Explanations

    terms related to laziness or slothfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to the concept of sleazy behavior

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interrupted
    -0.80
     diplom
    -0.72
    nas
    -0.64
    LESS
    -0.61
     UNESCO
    -0.60
     Nurs
    -0.59
    iates
    -0.58
    ians
    -0.57
     numbered
    -0.57
     Terminal
    -0.57
    POSITIVE LOGITS
    azy
    1.32
    eker
    1.27
    eper
    1.18
    igh
    1.12
    eping
    1.09
    ight
    1.08
    pt
    1.00
    uth
    0.98
    pload
    0.97
    aving
    0.96
    Activations Density 0.026%

    No Known Activations