© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 2988
    Prev
    Next
    INDEX
    Explanations

    instances of opinion and review articles

    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
    0:0.13
    1:0.02
    2:0.07
    3:0.26
    4:0.04
    5:0.07
    6:0.02
    7:0.07
    8:0.04
    9:0.02
    10:0.16
    11:0.04
    Negative Logits
     executives
    -2.37
     peers
    -2.13
     broadcasters
    -2.12
     institutions
    -2.10
     agencies
    -2.07
     Governments
    -2.04
     corporations
    -2.04
     nations
    -2.01
     governments
    -1.99
     officials
    -1.98
    POSITIVE LOGITS
     tutorial
    2.48
     addon
    2.30
     filler
    2.30
    ictionary
    2.22
     appendix
    2.14
    isode
    2.12
     compilation
    2.09
    ertation
    2.08
    cellent
    2.05
     recipe
    2.03
    Activations Density 0.224%

    No Known Activations