© 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. 4-RES-JB
    11. 1002
    Prev
    Next
    INDEX
    Explanations

    keywords related to a specific term or product named "Elite."

    oai_token-act-pair · gpt-3.5-turbo

    references to elite groups or organizations

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

    No Comments

    Negative Logits
    enegger
    -0.86
    tumblr
    -0.84
    ELL
    -0.74
    ascus
    -0.71
     stump
    -0.67
    ask
    -0.64
     compr
    -0.64
     gifted
    -0.63
    rien
    -0.62
    aper
    -0.62
    POSITIVE LOGITS
     Dangerous
    0.99
     Trooper
    0.91
     Trainer
    0.86
    imore
    0.76
     Dimensions
    0.76
    tainment
    0.76
    Ĥª
    0.76
    endale
    0.75
     Packs
    0.75
     Riders
    0.73
    Activations Density 0.020%

    No Known Activations