© 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. 15973
    Prev
    Next
    INDEX
    Explanations

    mentions of characters, stories, and themes related to societal structures and power dynamics

    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
    0:0.05
    1:0.02
    2:0.06
    3:0.24
    4:0.02
    5:0.06
    6:0.01
    7:0.06
    8:0.02
    9:0.02
    10:0.36
    11:0.02
    Negative Logits
     Barcl
    -2.03
    english
    -1.84
     Cyprus
    -1.83
     Rosa
    -1.82
     International
    -1.78
     Lafayette
    -1.78
    LP
    -1.74
     Colombia
    -1.72
    warning
    -1.71
     unfocusedRange
    -1.70
    POSITIVE LOGITS
     dominates
    2.99
     equals
    2.96
     enjoys
    2.92
     resides
    2.75
     earns
    2.72
     dictates
    2.71
     dictate
    2.54
     communicates
    2.53
     sleeps
    2.46
     ceases
    2.44
    Activations Density 0.341%

    No Known Activations