© 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. 8181
    Prev
    Next
    INDEX
    Explanations

    concepts related to legal or ethical responsibilities

    oai_token-act-pair · gpt-3.5-turbo

    words related to moral and legal responsibilities

    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
    pher
    -0.67
    ld
    -0.65
    ild
    -0.64
     Mong
    -0.64
    Tip
    -0.63
    Spe
    -0.61
     Glow
    -0.60
    icons
    -0.60
     Spe
    -0.60
     CAM
    -0.60
    POSITIVE LOGITS
     obligation
    3.79
     obligations
    3.22
     obligated
    2.03
     responsibilities
    1.92
     responsibility
    1.82
     duty
    1.70
     duties
    1.46
     liability
    1.46
     commitments
    1.44
     liabilities
    1.37
    Activations Density 0.010%

    No Known Activations