© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 13788
    Prev
    Next
    INDEX
    Explanations

    words related to serious, ethical, moral, and profound issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ethical and moral concerns in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zup
    -0.96
     effortlessly
    -0.78
    ansson
    -0.72
     Smooth
    -0.70
    oscope
    -0.67
     seamlessly
    -0.67
    deen
    -0.66
     Seconds
    -0.65
    ride
    -0.65
    apist
    -0.64
    POSITIVE LOGITS
     problems
    1.44
     concerns
    1.41
     implications
    1.40
     dangers
    1.33
     challenges
    1.33
     issues
    1.32
     vulnerabilities
    1.30
     shortcomings
    1.27
     questions
    1.26
     injust
    1.25
    Activations Density 0.263%

    No Known Activations