© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43648
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to the exercise of rights, particularly in legal or constitutional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.05
    3:0.05
    4:0.14
    5:0.02
    6:0.07
    7:0.43
    8:0.03
    9:0.03
    10:0.04
    11:0.06
    Negative Logits
    ominated
    -1.59
    liner
    -1.40
    quartered
    -1.39
    aughtered
    -1.37
    ungle
    -1.35
    itutes
    -1.34
    oice
    -1.32
    ospons
    -1.32
    ircraft
    -1.31
    itute
    -1.26
    POSITIVE LOGITS
     discretion
    2.28
     autonomy
    1.93
     patience
    1.93
     restraint
    1.81
     modesty
    1.77
     boundaries
    1.75
     rights
    1.73
    Relations
    1.70
     bounds
    1.67
    limits
    1.65
    Activations Density 0.004%

    No Known Activations