© 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. 11427
    Prev
    Next
    INDEX
    Explanations

    discussions about critical issues and potential threats, including those related to public health, economic challenges, and environmental impact

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to public health and safety concerns

    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
     Nope
    -0.90
     nicer
    -0.80
     prett
    -0.77
     Style
    -0.76
     Funny
    -0.75
     Pretty
    -0.72
    Pretty
    -0.72
     cheerful
    -0.71
    Nice
    -0.71
     classy
    -0.70
    POSITIVE LOGITS
     jeopard
    1.20
     impacting
    1.19
     adversely
    1.19
     destabil
    1.13
     impacts
    1.08
     exacerbated
    1.06
     exacerbate
    1.02
     disruption
    1.01
     endanger
    1.00
     disrupting
    1.00
    Activations Density 0.987%

    No Known Activations