© 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. 12-RES-JB
    11. 4076
    Prev
    Next
    INDEX
    Explanations

    mentions of cell proliferation and cell types

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to cells and cellular processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Logged
    -0.81
    gers
    -0.80
    ereo
    -0.79
    hend
    -0.78
    hers
    -0.75
    UD
    -0.69
    dated
    -0.67
    ickets
    -0.66
    EE
    -0.66
    hab
    -0.64
    POSITIVE LOGITS
    ular
    1.01
     membranes
    0.98
     membrane
    0.93
     apopt
    0.92
     proliferation
    0.90
    ularity
    0.85
     carcin
    0.84
    icidal
    0.83
    estial
    0.83
     biologist
    0.82
    Activations Density 0.038%

    No Known Activations