© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 15045
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations, specifically focusing on regions related to Latin America

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.03
    2:0.03
    3:0.22
    4:0.08
    5:0.03
    6:0.03
    7:0.24
    8:0.01
    9:0.04
    10:0.03
    11:0.15
    Negative Logits
     motor
    -2.31
    unity
    -2.26
    Sunday
    -2.23
    Motor
    -2.22
    nesday
    -2.20
    AMD
    -2.16
    Norm
    -2.13
    ��
    -2.07
    expensive
    -2.04
    enegger
    -2.00
    POSITIVE LOGITS
    ipel
    2.87
     Digest
    2.64
     Canada
    2.44
     globe
    2.43
    ibaba
    2.40
    zu
    2.39
     continent
    2.36
    ッド
    2.36
    Canada
    2.35
     hemisphere
    2.34
    Activations Density 0.003%

    No Known Activations