© 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. 9-ATT-KK
    11. 1335
    Prev
    Next
    INDEX
    Explanations

    instances of legal terminology and court-related 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
    0:0.07
    1:0.04
    2:0.12
    3:0.06
    4:0.19
    5:0.06
    6:0.06
    7:0.13
    8:0.06
    9:0.08
    10:0.04
    11:0.04
    Negative Logits
    yip
    -2.63
    76561
    -2.60
     tremend
    -2.56
    flix
    -2.45
     whis
    -2.28
     waterfall
    -2.27
     spam
    -2.24
     appar
    -2.20
     fundament
    -2.18
    atch
    -2.15
    POSITIVE LOGITS
     Judge
    4.42
    Judge
    4.35
     Justice
    4.09
    Justice
    3.81
     justices
    3.81
     jurors
    3.54
     appellate
    3.48
     Judges
    3.48
     Court
    3.44
     Lawyers
    3.34
    Activations Density 0.045%

    No Known Activations