© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14385
    Prev
    Next
    INDEX
    Explanations

    legal terminology and events related to court orders and sentences

    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
    0:0.02
    1:0.01
    2:0.03
    3:0.05
    4:0.05
    5:0.27
    6:0.04
    7:0.04
    8:0.01
    9:0.30
    10:0.02
    11:0.09
    Negative Logits
    icho
    -2.95
    rities
    -2.46
     loved
    -2.42
    ":[{"
    -2.41
    sometimes
    -2.40
    nces
    -2.35
     likes
    -2.31
    ゼウス
    -2.30
    luaj
    -2.27
    ilogy
    -2.27
    POSITIVE LOGITS
     pending
    4.01
     barring
    3.44
     barred
    3.38
     prohibiting
    3.33
     postp
    3.29
     conditional
    3.21
     against
    3.21
     suspending
    3.20
     permitting
    3.18
     indefinitely
    3.15
    Activations Density 0.254%

    No Known Activations