© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 702
    Prev
    Next
    INDEX
    Explanations

    references to musical groups and their performances

    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
    0:0.12
    1:0.04
    2:0.10
    3:0.10
    4:0.07
    5:0.06
    6:0.05
    7:0.08
    8:0.20
    9:0.04
    10:0.04
    11:0.04
    Negative Logits
     Walsh
    -3.37
     Tolkien
    -3.27
     Cato
    -3.18
     Belichick
    -3.12
     Ulster
    -2.99
     Buchanan
    -2.97
     Wem
    -2.91
    ichick
    -2.90
     Manit
    -2.87
     Berkshire
    -2.85
    POSITIVE LOGITS
    �
    4.54
    �
    4.53
     �
    4.49
    �
    4.32
    ㅋㅋ
    4.27
    �
    4.21
     �
    4.04
     [+
    4.01
    �
    4.01
    �
    3.99
    Activations Density 0.025%

    No Known Activations