© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 9910
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal processes and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.03
    2:0.13
    3:0.05
    4:0.05
    5:0.04
    6:0.20
    7:0.04
    8:0.04
    9:0.26
    10:0.04
    11:0.02
    Negative Logits
    anka
    -4.03
     broccoli
    -3.63
    hent
    -3.62
    apon
    -3.47
     Andrews
    -3.46
     Scarborough
    -3.45
     Hyde
    -3.40
     Panama
    -3.37
     sewage
    -3.35
    Ash
    -3.31
    POSITIVE LOGITS
     Jury
    7.13
     jurors
    6.94
     jury
    6.56
     jur
    5.89
     Jur
    5.79
     verdict
    4.04
    judicial
    3.90
    uries
    3.85
    jury
    3.77
     inquest
    3.73
    Activations Density 0.001%

    No Known Activations