© 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. 43568
    Prev
    Next
    INDEX
    Explanations

    common articles and prepositions that indicate locations or relationships

    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
    0:0.01
    1:0.01
    2:0.04
    3:0.04
    4:0.15
    5:0.02
    6:0.14
    7:0.35
    8:0.03
    9:0.03
    10:0.06
    11:0.06
    Negative Logits
     wont
    -1.42
    rats
    -1.33
    itsch
    -1.32
     essentials
    -1.30
    ilitarian
    -1.30
     lawy
    -1.30
    avers
    -1.27
    ér
    -1.27
    iferation
    -1.27
    jab
    -1.25
    POSITIVE LOGITS
     fray
    2.01
    phabet
    1.69
     orbit
    1.65
    estamp
    1.51
    ulia
    1.50
     captcha
    1.50
     ranks
    1.49
     Via
    1.47
     Wonderland
    1.38
     Corps
    1.38
    Activations Density 0.016%

    No Known Activations