© 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. 19701
    Prev
    Next
    INDEX
    Explanations

    phrases related to disappointment and performance expectations in a professional context

    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
    0:0.24
    1:0.11
    2:0.12
    3:0.05
    4:0.03
    5:0.02
    6:0.06
    7:0.07
    8:0.03
    9:0.03
    10:0.13
    11:0.06
    Negative Logits
    76561
    -3.52
    Kin
    -3.51
     Okin
    -3.47
     Okinawa
    -3.10
     Cogn
    -3.09
     gren
    -3.05
    cheat
    -3.01
     Blade
    -3.00
     Estonia
    -2.98
     Eston
    -2.98
    POSITIVE LOGITS
     Moses
    9.74
     Pharaoh
    6.25
     Exodus
    5.67
     Torah
    5.56
     Morsi
    5.43
     Sinai
    5.40
    Egypt
    5.24
     Egyptians
    5.12
     Egyptian
    4.71
     Hebrew
    4.71
    Activations Density 0.002%

    No Known Activations