© 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. 1948
    Prev
    Next
    INDEX
    Explanations

    references to specific historical events and locations related to Buffalo

    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
    0:0.10
    1:0.01
    2:0.06
    3:0.05
    4:0.03
    5:0.05
    6:0.15
    7:0.04
    8:0.28
    9:0.13
    10:0.02
    11:0.02
    Negative Logits
     Chilean
    -4.28
     Chile
    -3.94
     Scientology
    -3.76
     GSL
    -3.62
     Martian
    -3.59
     ESV
    -3.58
     Scient
    -3.52
     ell
    -3.50
     Karn
    -3.46
     Choi
    -3.41
    POSITIVE LOGITS
     Buffalo
    10.23
     Sabres
    9.65
    Buff
    8.79
     Bills
    8.49
     Niagara
    6.57
     buffalo
    5.99
     Erie
    5.91
     Fitzpatrick
    5.67
     Syracuse
    5.42
    buff
    5.37
    Activations Density 0.031%

    No Known Activations