© 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. 0-RES-JB
    11. 8220
    Prev
    Next
    INDEX
    Explanations

    terms related to moral concepts such as altruism, moral universe, moral courage, moral legitimacy, moral authority, ethical systems, moral duty, and moral responsibility

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "moral" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    swick
    -0.84
    hops
    -0.76
     Pwr
    -0.74
     GHz
    -0.74
     ASUS
    -0.72
    OTS
    -0.72
     Pavilion
    -0.72
    irl
    -0.70
    Bas
    -0.69
     ASAP
    -0.69
    POSITIVE LOGITS
     moral
    3.24
    moral
    2.83
     Moral
    2.46
     morally
    2.24
     morality
    2.24
     ethical
    2.06
     morals
    2.00
     immoral
    1.84
     conscience
    1.57
     philosophical
    1.49
    Activations Density 0.023%

    No Known Activations