© 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. 9-RES-JB
    11. 15879
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethics and standards

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ethical standards and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     latent
    -0.65
     nifty
    -0.64
     unwitting
    -0.62
     giant
    -0.62
     obscure
    -0.61
     coincidence
    -0.61
     moot
    -0.60
     tantal
    -0.59
     bombs
    -0.59
     ado
    -0.59
    POSITIVE LOGITS
     regardless
    1.11
     irrespective
    1.06
     wherever
    0.87
     respectfully
    0.80
    0.78
     throughout
    0.78
     RESP
    0.77
     whenever
    0.76
     safegu
    0.75
    .''.
    0.75
    Activations Density 0.605%

    No Known Activations