© 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. 10051
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Just" followed by a verb or noun

    oai_token-act-pair · gpt-3.5-turbo

    uses of the word "Just" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ses
    -0.64
    Pg
    -0.63
     seiz
    -0.62
    pires
    -0.62
     bottleneck
    -0.61
     corpus
    -0.58
    ilater
    -0.57
    rb
    -0.55
    apolis
    -0.53
    OA
    -0.51
    POSITIVE LOGITS
     kidding
    1.17
    ifications
    1.04
    ifiable
    1.00
     imagine
    0.98
    ices
    0.92
    if
    0.91
    ifying
    0.91
    ified
    0.88
     beware
    0.88
    ification
    0.86
    Activations Density 0.050%

    No Known Activations