© 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. 10-ATT-KK
    11. 13220
    Prev
    Next
    INDEX
    Explanations

    overall sentiments related to personal experiences and family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.06
    2:0.06
    3:0.05
    4:0.06
    5:0.03
    6:0.16
    7:0.13
    8:0.02
    9:0.05
    10:0.10
    11:0.06
    Negative Logits
     amphib
    -3.47
     Fisheries
    -3.16
     Franks
    -3.01
     Witt
    -2.95
     Pir
    -2.95
     Ples
    -2.94
     Bart
    -2.93
     Aqu
    -2.92
     Rapt
    -2.90
     Drake
    -2.88
    POSITIVE LOGITS
     miners
    4.95
     miner
    4.38
    Merit
    3.46
     hashing
    3.21
     strikers
    3.00
     socialists
    2.96
    union
    2.88
     socialism
    2.86
    urses
    2.82
     Maduro
    2.79
    Activations Density 0.001%

    No Known Activations