© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-ATT-KK
    11. 43050
    Prev
    Next
    INDEX
    Explanations

    instances of the word "van" and various forms of "de" and "du."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.20
    2:0.03
    3:0.04
    4:0.03
    5:0.28
    6:0.04
    7:0.02
    8:0.06
    9:0.09
    10:0.05
    11:0.03
    Negative Logits
    hist
    -2.06
    arian
    -2.01
    gie
    -1.85
    press
    -1.82
    atem
    -1.79
    only
    -1.75
    avid
    -1.75
    itud
    -1.74
    stores
    -1.74
    estic
    -1.73
    POSITIVE LOGITS
     Thrones
    2.00
     Wag
    1.92
     Leg
    1.87
     Pt
    1.83
     Hyde
    1.81
     Shadows
    1.76
     Term
    1.76
     Thames
    1.71
     Strikes
    1.71
     Furious
    1.67
    Activations Density 0.006%

    No Known Activations