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. 1-ATT-KK
    6. 6418
    Prev
    Next
    INDEX
    Explanations

    names of countries and geopolitical entities, especially focusing on Moldova and Russia

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.22
    1:0.06
    2:0.04
    3:0.03
    4:0.05
    5:0.04
    6:0.22
    7:0.05
    8:0.05
    9:0.04
    10:0.03
    11:0.10
    Negative Logits
     AAP
    -1.49
     occasional
    -1.49
     escort
    -1.44
    uably
    -1.44
     conven
    -1.43
     Galile
    -1.40
     cooldown
    -1.40
     TAG
    -1.39
    riott
    -1.38
    )].
    -1.36
    POSITIVE LOGITS
    grain
    1.73
    Monster
    1.60
    �
    1.60
     fungus
    1.58
    女
    1.57
    sample
    1.56
    stros
    1.54
     unemploy
    1.52
    worms
    1.49
    rafted
    1.48
    Activations Density 0.007%

    No Known Activations