© 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. 5-ATT-KK
    11. 43654
    Prev
    Next
    INDEX
    Explanations

    repeated prepositional phrases indicating relationships or belonging

    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
    0:0.03
    1:0.02
    2:0.07
    3:0.08
    4:0.17
    5:0.03
    6:0.02
    7:0.34
    8:0.03
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
    uez
    -1.58
    daq
    -1.57
     Tsukuyomi
    -1.54
    ebook
    -1.50
    ebted
    -1.46
     hypot
    -1.42
    achus
    -1.37
    quished
    -1.36
     freely
    -1.34
    wered
    -1.33
    POSITIVE LOGITS
    burgh
    1.33
     toughness
    1.30
     sophistication
    1.29
     Hack
    1.28
     Colour
    1.28
     refinement
    1.28
     Studio
    1.28
     engagement
    1.26
    rity
    1.25
     professionalism
    1.23
    Activations Density 0.001%

    No Known Activations