© 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. 21110
    Prev
    Next
    INDEX
    Explanations

    terms related to laws and regulations, particularly those concerning prohibited or banned activities

    oai_token-act-pair · gpt-3.5-turbo

    references to bans or prohibitions on various substances and practices

    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
    herty
    -0.70
    abase
    -0.67
     Devi
    -0.67
    icho
    -0.64
    romy
    -0.63
    yssey
    -0.63
    awar
    -0.62
    response
    -0.61
    ®
    -0.61
    ampa
    -0.61
    POSITIVE LOGITS
     altogether
    1.24
     except
    1.03
     imports
    1.02
     punishable
    0.95
     outright
    0.93
     exemptions
    0.91
     unless
    0.90
     entirely
    0.89
     exports
    0.87
     rentals
    0.87
    Activations Density 0.267%

    No Known Activations