© 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. 2-RES-JB
    11. 405
    Prev
    Next
    INDEX
    Explanations

    the transition word "Moreover"

    oai_token-act-pair · gpt-4-turbo

    concluding statements or additional information in a paragraph

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Moreover."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    crow
    -0.71
    76561
    -0.67
    don
    -0.63
    ê
    -0.62
    ding
    -0.61
    bur
    -0.60
     straw
    -0.59
    uci
    -0.58
    advertising
    -0.57
    psc
    -0.57
    POSITIVE LOGITS
     guiActiveUn
    0.85
    nesses
    0.80
    ront
    0.78
    NESS
    0.75
    ctr
    0.74
    ombat
    0.72
    entimes
    0.71
    ommel
    0.70
    verage
    0.70
    æ©Ł
    0.70
    Activations Density 0.007%

    No Known Activations