© 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. 14867
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "root"

    oai_token-act-pair · gpt-3.5-turbo

    references to "root" in various contexts

    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
     Faul
    -0.82
     Mayhem
    -0.80
    ittee
    -0.76
    casters
    -0.75
     Emin
    -0.71
    Town
    -0.71
    imon
    -0.69
    Magazine
    -0.67
    NRS
    -0.65
     EDITION
    -0.65
    POSITIVE LOGITS
     root
    4.06
    root
    2.61
     Root
    2.57
    Root
    2.52
     roots
    2.18
     rooting
    2.00
     Roots
    1.82
     rooted
    1.52
    roots
    1.49
     stem
    1.07
    Activations Density 0.014%

    No Known Activations