Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10738
    Prev
    Next
    INDEX
    Explanations

    phrases related to fairness and equity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.03
    2:0.05
    3:0.15
    4:0.02
    5:0.04
    6:0.12
    7:0.18
    8:0.04
    9:0.05
    10:0.07
    11:0.17
    Negative Logits
    acid
    -1.28
    ゼウス
    -1.14
    ESE
    -1.13
    ikuman
    -1.13
    �士
    -1.11
    ダ
    -1.10
    atan
    -1.10
    uden
    -1.10
    swing
    -1.08
    enko
    -1.07
    POSITIVE LOGITS
     equitable
    1.22
    parency
    1.18
     applicable
    1.12
    lihood
    1.12
     impartial
    1.05
     comparison
    1.02
     adjud
    1.02
     faire
    1.02
     reporting
    1.00
     outcome
    0.98
    Activations Density 0.005%

    No Known Activations