© 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. 5-ATT-KK
    11. 2318
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations, especially states and cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.21
    2:0.03
    3:0.05
    4:0.01
    5:0.14
    6:0.01
    7:0.01
    8:0.05
    9:0.17
    10:0.05
    11:0.06
    Negative Logits
    usted
    -1.33
    SPONSORED
    -1.23
    inx
    -1.22
    aez
    -1.20
    sted
    -1.19
    BTC
    -1.18
    fecture
    -1.15
    amn
    -1.14
    hatt
    -1.13
    ibo
    -1.13
    POSITIVE LOGITS
     Yor
    1.27
     Various
    1.12
     Than
    1.11
     Tau
    1.06
    orgetown
    1.03
     Ober
    1.03
     Orient
    1.03
     Sahara
    1.02
     Mandatory
    1.02
     Net
    1.00
    Activations Density 0.231%

    No Known Activations