© 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. 0-RES-JB
    11. 6648
    Prev
    Next
    INDEX
    Explanations

    proper nouns, potentially related to people's names or places

    oai_token-act-pair · gpt-3.5-turbo

    names that end with "strom."

    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
     Pix
    -0.78
     share
    -0.74
     peer
    -0.69
     poss
    -0.68
     favour
    -0.66
     basis
    -0.64
     co
    -0.63
     honorary
    -0.63
     tou
    -0.62
     sharing
    -0.62
    POSITIVE LOGITS
    strom
    4.83
    quist
    1.94
    lund
    1.86
    gren
    1.66
    qv
    1.61
    holm
    1.48
    berg
    1.27
    sted
    1.24
    sson
    1.22
    gaard
    1.21
    Activations Density 0.013%

    No Known Activations