© 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. 16093
    Prev
    Next
    INDEX
    Explanations

    positive sentiments or hopefulness in sports contexts

    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
    0:0.07
    1:0.02
    2:0.06
    3:0.06
    4:0.04
    5:0.05
    6:0.06
    7:0.07
    8:0.43
    9:0.04
    10:0.04
    11:0.02
    Negative Logits
     Liberia
    -4.22
     Ethiopian
    -4.12
    African
    -4.10
     Ethiopia
    -4.03
     Chilean
    -3.92
     Guatem
    -3.81
     Ghana
    -3.78
     Charleston
    -3.78
     African
    -3.75
     ANC
    -3.75
    POSITIVE LOGITS
     Leafs
    7.91
    Toronto
    6.67
     Toronto
    6.04
     Maple
    5.20
    Ont
    4.86
     TTC
    4.57
     Ontario
    4.55
     Ottawa
    4.39
     Niagara
    4.38
     Tory
    4.09
    Activations Density 0.026%

    No Known Activations