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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 11149
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "India" in various contexts

    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
    0:0.02
    1:0.29
    2:0.02
    3:0.18
    4:0.02
    5:0.09
    6:0.02
    7:0.14
    8:0.09
    9:0.01
    10:0.03
    11:0.02
    Negative Logits
     glim
    -2.98
    depending
    -2.79
    oresc
    -2.64
    spe
    -2.62
    bage
    -2.38
    illet
    -2.35
    vous
    -2.33
    ヴァ
    -2.29
    AGES
    -2.28
    pron
    -2.22
    POSITIVE LOGITS
     Secondly
    3.25
     Mongolia
    2.53
     secondly
    2.39
     DPRK
    2.35
     Mysterious
    2.30
     Pakistan
    2.28
     Malays
    2.21
    Secondly
    2.14
     Mald
    2.14
     Nepal
    2.14
    Activations Density 0.003%

    No Known Activations