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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 15466
    Prev
    Next
    INDEX
    Explanations

    references to locations or geographic terms

    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
    0:0.04
    1:0.01
    2:0.05
    3:0.11
    4:0.07
    5:0.09
    6:0.03
    7:0.06
    8:0.40
    9:0.02
    10:0.04
    11:0.04
    Negative Logits
    Houston
    -4.72
     Irving
    -4.10
     Houston
    -4.06
     Hunts
    -3.76
    Dallas
    -3.71
     Venezuel
    -3.62
    Texas
    -3.57
    Austin
    -3.51
     Texas
    -3.49
     Asheville
    -3.42
    POSITIVE LOGITS
    agna
    4.04
    vati
    3.82
     Serie
    3.64
     Milan
    3.35
     Rossi
    3.31
    Italy
    3.27
    Italian
    3.24
    enza
    3.20
     Aless
    3.20
     Malfoy
    3.18
    Activations Density 0.032%

    No Known Activations