© 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 EvalsExportsinterp-engineNEWAPI 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. 9925
    Prev
    Next
    INDEX
    Explanations

    queries or questions starting with "Who"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Who" as a recurring element, indicating inquiries about individuals or entities

    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
    MER
    -0.86
    PORT
    -0.68
     Hyde
    -0.68
    rog
    -0.63
     Rye
    -0.62
    York
    -0.61
    BACK
    -0.60
    personal
    -0.58
     Et
    -0.57
    OOL
    -0.57
    POSITIVE LOGITS
    soever
    1.16
    ever
    1.02
    oping
    1.01
    abouts
    0.96
     else
    0.93
    oped
    0.89
     cares
    0.86
     knows
    0.85
    osh
    0.82
    zbollah
    0.81
    Activations Density 0.085%

    No Known Activations