© 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. 11-RES-JB
    11. 2841
    Prev
    Next
    INDEX
    Explanations

    phrases related to violations of rules or laws

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal or regulatory violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arger
    -0.84
     Tycoon
    -0.84
    NetMessage
    -0.76
    roxy
    -0.70
    ilts
    -0.63
    zie
    -0.60
    igmat
    -0.59
    rica
    -0.58
    river
    -0.58
     glamorous
    -0.58
    POSITIVE LOGITS
     violations
    1.00
    viol
    0.98
     violation
    0.90
     punishable
    0.88
     committed
    0.83
     Viol
    0.79
     thereof
    0.76
     viol
    0.76
    lig
    0.72
     infring
    0.70
    Activations Density 0.076%

    No Known Activations