© 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 EvalsExportsinterp-engineNEWAPI 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. 4101
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethical issues and violations

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to ethics

    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
    nces
    -0.78
    upt
    -0.76
    xual
    -0.75
    ings
    -0.72
    nant
    -0.71
    down
    -0.71
    oday
    -0.71
    jong
    -0.70
    LOAD
    -0.68
     Jub
    -0.66
    POSITIVE LOGITS
    onomic
    1.01
     dile
    0.91
     watchdog
    0.82
     violations
    0.82
     waivers
    0.80
    onom
    0.78
     breaches
    0.78
     hazard
    0.75
    utical
    0.74
     considerations
    0.74
    Activations Density 0.049%

    No Known Activations