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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 7625
    Prev
    Next
    INDEX
    Explanations

    references to the Rohingya people and their struggles, specifically regarding their persecution and displacement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.01
    2:0.18
    3:0.07
    4:0.03
    5:0.11
    6:0.02
    7:0.08
    8:0.18
    9:0.02
    10:0.04
    11:0.02
    Negative Logits
     Yon
    -2.56
    Unix
    -2.32
     Corvette
    -2.28
    ukemia
    -2.28
     metast
    -2.27
    $$
    -2.24
     addict
    -2.23
     tumors
    -2.19
     Moose
    -2.16
     Roller
    -2.15
    POSITIVE LOGITS
     Rohing
    3.50
     Rohingya
    3.04
     UNHCR
    2.76
    berra
    2.55
     resettlement
    2.54
    nesty
    2.50
    �醒
    2.40
     persecution
    2.38
    agar
    2.35
     Dw
    2.33
    Activations Density 0.009%

    No Known Activations