© 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. 0-RES-JB
    11. 12392
    Prev
    Next
    INDEX
    Explanations

    adjectives and phrases related to virtue

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to virtue and moral qualities

    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
     Scan
    -0.73
    fo
    -0.73
    FO
    -0.71
    bers
    -0.65
     scanner
    -0.64
     Aden
    -0.63
    arger
    -0.62
     Alert
    -0.62
     estimates
    -0.62
    zilla
    -0.61
    POSITIVE LOGITS
     virtue
    3.82
     virtues
    2.36
     Virtue
    2.32
     virtuous
    1.65
    virt
    1.35
     piety
    1.25
     righteousness
    1.21
     merit
    1.15
     decency
    1.11
     goodness
    1.10
    Activations Density 0.026%

    No Known Activations