© 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 EvalsExportsAPI 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. 10-RES-JB
    11. 3332
    Prev
    Next
    INDEX
    Explanations

    mentions of elevators and related activities or features

    oai_token-act-pair · gpt-3.5-turbo

    terms related to elevators and elevation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.82
    nia
    -0.81
    ned
    -0.80
    ters
    -0.76
    ãģ¦
    -0.75
    fulness
    -0.74
    neg
    -0.72
    cheat
    -0.71
    nar
    -0.70
    kered
    -0.70
    POSITIVE LOGITS
     elev
    0.95
     heights
    0.94
     shaft
    0.88
     ceilings
    0.86
     Everest
    0.83
     elevation
    0.80
     elevate
    0.76
    ipl
    0.75
    uations
    0.75
    xual
    0.75
    Activations Density 0.075%

    No Known Activations