© 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. 10489
    Prev
    Next
    INDEX
    Explanations

    judicial language regarding court rulings and decisions

    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
    1:0.02
    2:0.03
    3:0.06
    4:0.20
    5:0.13
    6:0.09
    7:0.10
    8:0.02
    9:0.19
    10:0.03
    11:0.04
    Negative Logits
     weap
    -2.63
    OTOS
    -2.33
    76561
    -2.27
    natureconservancy
    -2.23
    advertising
    -2.19
     EVENTS
    -2.18
     scen
    -2.10
    geries
    -2.09
     INFO
    -2.05
    erest
    -2.05
    POSITIVE LOGITS
     ruled
    3.51
     overturned
    3.44
     sided
    3.25
     upheld
    3.25
     argued
    3.09
     reinstated
    3.04
     invalid
    2.98
     reversed
    2.96
     unconstitutional
    2.96
     dissenting
    2.96
    Activations Density 0.298%

    No Known Activations