© 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. 9-ATT-KK
    11. 8304
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.03
    3:0.06
    4:0.02
    5:0.03
    6:0.08
    7:0.03
    8:0.04
    9:0.54
    10:0.02
    11:0.02
    Negative Logits
     Nichols
    -3.58
     Nicholson
    -3.40
     Witt
    -3.40
     Ges
    -3.36
     Mania
    -3.29
     Ludwig
    -3.28
     Wass
    -3.26
     Wilhelm
    -3.26
     Molly
    -3.25
     Muse
    -3.25
    POSITIVE LOGITS
    ar
    6.47
    AR
    6.33
    ars
    5.45
    arth
    5.27
    rar
    5.21
    ARC
    5.19
     AR
    5.18
    ARA
    5.01
    arr
    4.98
    ARS
    4.93
    Activations Density 0.078%

    No Known Activations