© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22018
    Prev
    Next
    INDEX
    Explanations

    situations involving legal actions or rulings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.07
    2:0.04
    3:0.20
    4:0.04
    5:0.08
    6:0.13
    7:0.05
    8:0.06
    9:0.06
    10:0.09
    11:0.04
    Negative Logits
     Contracts
    -1.32
     channels
    -1.16
    thumbnails
    -1.14
     formations
    -1.14
     interfaces
    -1.12
     formats
    -1.11
     portals
    -1.11
     Challenges
    -1.10
     realms
    -1.10
     levers
    -1.08
    POSITIVE LOGITS
    athi
    1.15
     spokesperson
    1.11
     attacker
    1.07
    ç
    1.07
     apology
    1.06
    lander
    1.05
    tale
    1.02
    bodied
    1.02
    ebin
    1.02
    rag
    1.02
    Activations Density 0.063%

    No Known Activations