© 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. 9526
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names among a list of entities

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "among others."

    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
     prol
    -0.75
    irez
    -0.66
    oric
    -0.64
     commute
    -0.62
    PORT
    -0.60
    oldemort
    -0.58
     KL
    -0.57
    nery
    -0.57
    ORY
    -0.57
    penter
    -0.57
    POSITIVE LOGITS
    warts
    0.95
     whom
    0.82
    wart
    0.77
    Īè
    0.76
    st
    0.76
     Tradable
    0.75
    ership
    0.74
    IJ
    0.73
    %%%%
    0.73
    among
    0.72
    Activations Density 0.021%

    No Known Activations