© 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 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. 2510
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations or cities

    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
    0:0.06
    1:0.01
    2:0.03
    3:0.11
    4:0.03
    5:0.09
    6:0.03
    7:0.04
    8:0.14
    9:0.02
    10:0.04
    11:0.34
    Negative Logits
     ―
    -3.78
    Newsletter
    -3.59
    Enlarge
    -3.44
    ADVERTISEMENT
    -3.28
    —"
    -2.97
    Torrent
    -2.89
    "—
    -2.79
    ——
    -2.74
     —
    -2.64
    ──
    -2.57
    POSITIVE LOGITS
     IA
    3.35
     TX
    3.33
     OR
    3.15
     KS
    3.13
     NJ
    3.08
     WI
    2.99
     VA
    2.98
     TN
    2.91
     MA
    2.88
     
    2.84
    Activations Density 0.003%

    No Known Activations