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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22098
    Prev
    Next
    INDEX
    Explanations

    phrases related to policies concerning education and government funding

    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
    0:0.04
    1:0.49
    2:0.04
    3:0.03
    4:0.03
    5:0.03
    6:0.05
    7:0.04
    8:0.04
    9:0.05
    10:0.07
    11:0.03
    Negative Logits
     Lovecraft
    -3.28
     Arkham
    -2.88
    lectic
    -2.65
    inburgh
    -2.57
    Philadelphia
    -2.49
    phia
    -2.44
     Plymouth
    -2.43
    Thompson
    -2.41
    sonian
    -2.37
    Clock
    -2.37
    POSITIVE LOGITS
     Duterte
    3.12
     Rohingya
    3.06
     Filipino
    3.01
     Hindi
    2.93
     Suk
    2.91
     Chin
    2.87
     Malaysian
    2.77
     ko
    2.68
     Bin
    2.67
     Filip
    2.67
    Activations Density 0.100%

    No Known Activations