© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17663
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Ru"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the element Ruthenium (Ru) in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.83
     Seym
    -0.81
     Remastered
    -0.74
    croft
    -0.69
    sie
    -0.69
    lihood
    -0.68
    20439
    -0.67
     HELL
    -0.61
     Cerberus
    -0.60
    manship
    -0.60
    POSITIVE LOGITS
    pees
    1.32
    pee
    1.16
    ination
    1.04
    inous
    1.02
    pport
    1.00
    pert
    0.97
    ined
    0.97
    wered
    0.96
    pton
    0.96
    ussia
    0.95
    Activations Density 0.021%

    No Known Activations