© 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. 3-ATT-KK
    6. 11035
    Prev
    Next
    INDEX
    Explanations

    specific sequences or patterns related to geographic locations and associated political entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.07
    3:0.37
    4:0.03
    5:0.02
    6:0.06
    7:0.07
    8:0.04
    9:0.10
    10:0.06
    11:0.07
    Negative Logits
    ヴァ
    -1.51
    王
    -1.28
    イト
    -1.26
    uminati
    -1.21
    aturdays
    -1.19
     Argentine
    -1.18
     largeDownload
    -1.17
     Illum
    -1.16
     sinks
    -1.16
     elig
    -1.16
    POSITIVE LOGITS
    abus
    1.42
    doi
    1.35
    rex
    1.34
    oran
    1.26
    ote
    1.24
    UTF
    1.24
    yll
    1.23
    uple
    1.23
    oslav
    1.22
    ################
    1.21
    Activations Density 0.012%

    No Known Activations