© 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. 13010
    Prev
    Next
    INDEX
    Explanations

    key terms related to significant agreements and developments in various contexts, particularly with political or economic implications

    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
    0:0.07
    1:0.02
    2:0.12
    3:0.23
    4:0.02
    5:0.09
    6:0.02
    7:0.05
    8:0.05
    9:0.01
    10:0.25
    11:0.01
    Negative Logits
    Occ
    -2.23
    pmwiki
    -2.19
     averages
    -2.19
     disliked
    -2.13
     randomly
    -2.08
     feud
    -2.08
     complained
    -2.04
     brut
    -2.03
     complaints
    -2.03
     varies
    -1.98
    POSITIVE LOGITS
     milestone
    3.22
     breakthrough
    3.17
     promise
    2.88
    bold
    2.81
     culmination
    2.76
     easing
    2.76
     transformative
    2.74
     accomplishment
    2.73
     promising
    2.72
     groundbreaking
    2.72
    Activations Density 0.398%

    No Known Activations