© 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. 9-RES-JB
    11. 11698
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "abb", specifically at different activation levels

    oai_token-act-pair · gpt-3.5-turbo

    references to specific terms related to "Abbott."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    piece
    -0.72
    ptives
    -0.66
     Cheong
    -0.63
    govtrack
    -0.63
    stanbul
    -0.63
     Gutenberg
    -0.61
     obser
    -0.60
    xia
    -0.59
     erosion
    -0.59
    stal
    -0.59
    POSITIVE LOGITS
    ucket
    1.03
    itt
    1.02
    arella
    0.98
    itte
    0.95
    atical
    0.90
    its
    0.90
    atar
    0.89
    inic
    0.86
    ler
    0.86
    inical
    0.86
    Activations Density 0.029%

    No Known Activations