© 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. 6-RES-JB
    11. 17883
    Prev
    Next
    INDEX
    Explanations

    phrases related to risk, impact, and causation

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that indicate risk or harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unic
    -0.68
    odo
    -0.66
    ©¶æ
    -0.64
    rounder
    -0.62
     apiece
    -0.62
    ocious
    -0.60
    ebook
    -0.60
    usp
    -0.58
    raph
    -0.56
    amer
    -0.55
    POSITIVE LOGITS
    particularly
    0.76
    eele
    0.71
     namely
    0.70
    especially
    0.68
     outweigh
    0.64
     Particularly
    0.64
    aeda
    0.62
    Whereas
    0.62
     Whereas
    0.60
    bda
    0.60
    Activations Density 1.094%

    No Known Activations