© 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. 16363
    Prev
    Next
    INDEX
    Explanations

    negative sentiments expressed through words and phrases

    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
    0:0.05
    1:0.06
    2:0.03
    3:0.03
    4:0.03
    5:0.04
    6:0.03
    7:0.06
    8:0.02
    9:0.20
    10:0.22
    11:0.16
    Negative Logits
     Carb
    -2.47
     Stab
    -2.35
     Tas
    -2.25
     explorer
    -2.20
     rall
    -2.18
    avis
    -2.18
     Sever
    -2.15
     openings
    -2.12
     dissolution
    -2.11
     Fl
    -2.08
    POSITIVE LOGITS
    udeb
    2.90
    hing
    2.78
     sh
    2.70
    hai
    2.69
    natureconservancy
    2.66
    Chel
    2.63
    yah
    2.54
    het
    2.54
    haw
    2.53
    hya
    2.53
    Activations Density 0.001%

    No Known Activations