© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21985
    Prev
    Next
    INDEX
    Explanations

    references to violations of rules or regulations, particularly regarding discipline and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.04
    2:0.04
    3:0.04
    4:0.07
    5:0.02
    6:0.07
    7:0.09
    8:0.02
    9:0.08
    10:0.03
    11:0.43
    Negative Logits
    iris
    -2.38
     istg
    -2.29
    naissance
    -2.27
    agonist
    -2.26
    ppel
    -2.22
    ocamp
    -2.09
    Rus
    -2.06
    ebted
    -2.00
    ilant
    -1.99
    lycer
    -1.97
    POSITIVE LOGITS
     rules
    5.36
     guidelines
    5.34
     regulations
    5.11
     laws
    5.00
     standards
    4.76
     norms
    4.56
     statutes
    4.44
     requirements
    4.38
     prohibitions
    4.37
     restrictions
    4.32
    Activations Density 1.344%

    No Known Activations