© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21172
    Prev
    Next
    INDEX
    Explanations

    statements or claims involving verification and confirmation

    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
    0:0.07
    1:0.08
    2:0.03
    3:0.04
    4:0.04
    5:0.03
    6:0.04
    7:0.44
    8:0.03
    9:0.05
    10:0.05
    11:0.05
    Negative Logits
     CAL
    -2.95
     Lime
    -2.89
     Cal
    -2.81
    alin
    -2.77
     Monte
    -2.75
     Lat
    -2.69
     Flore
    -2.68
    alle
    -2.67
     Tur
    -2.66
     Mun
    -2.63
    POSITIVE LOGITS
    043
    2.94
     starship
    2.73
     Ukip
    2.70
    EEK
    2.69
     HMS
    2.64
     apostles
    2.60
    ORPG
    2.59
     Skydragon
    2.58
     Hitchcock
    2.57
    steen
    2.54
    Activations Density 0.033%

    No Known Activations