© 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. 2-RES-JB
    11. 22540
    Prev
    Next
    INDEX
    Explanations

    words related to chemical compounds or names, specifically those ending in 'ene'

    oai_token-act-pair · gpt-3.5-turbo

    words related to the chemical compound "ene"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    frames
    -0.91
     retard
    -0.71
    deck
    -0.69
    è¦ļéĨĴ
    -0.66
    tub
    -0.66
    talk
    -0.65
    frame
    -0.65
    STER
    -0.65
    gerald
    -0.63
    ties
    -0.63
    POSITIVE LOGITS
    uve
    1.17
    utics
    1.17
    utical
    1.16
    alogy
    1.05
    esis
    0.96
    lette
    0.94
    volent
    0.92
    agles
    0.91
    lements
    0.90
     Wenger
    0.90
    Activations Density 0.008%

    No Known Activations