© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 11905
    Prev
    Next
    INDEX
    Explanations

    terms related to specific chemical compounds and their properties

    oai_token-act-pair · gpt-3.5-turbo

    the presence of various chemical compounds or elements, specifically those ending in "ene."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istically
    -0.77
    frames
    -0.76
    DOWN
    -0.76
    gerald
    -0.75
    istani
    -0.74
    tub
    -0.73
    ties
    -0.72
    displayText
    -0.72
    uitous
    -0.71
    DOC
    -0.71
    POSITIVE LOGITS
    uve
    1.17
    utics
    1.11
    utical
    1.05
    alogy
    1.01
     Wenger
    0.97
    agles
    0.96
    volent
    0.88
    lements
    0.88
    quin
    0.87
    utic
    0.85
    Activations Density 0.024%

    No Known Activations