© 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. 9-RES-JB
    11. 10123
    Prev
    Next
    INDEX
    Explanations

    phrases related to violations of laws, rights, or agreements

    oai_token-act-pair · gpt-3.5-turbo

    incidences of the word "violate" or its variants in the context of rights or laws being infringed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rich
    -0.74
    iris
    -0.74
    DragonMagazine
    -0.72
    mad
    -0.70
    gin
    -0.69
    rising
    -0.68
    rose
    -0.66
     helm
    -0.63
     anecd
    -0.63
    ript
    -0.62
    POSITIVE LOGITS
     treaties
    0.95
     laws
    0.94
     constitutional
    0.93
     Laws
    0.90
     Constitutional
    0.89
     confidentiality
    0.88
     regulations
    0.86
     norms
    0.85
     Rule
    0.84
     statutes
    0.83
    Activations Density 0.099%

    No Known Activations