© 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. 17834
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to organizations, agencies, and public figures in political contexts

    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
    0:0.11
    1:0.01
    2:0.05
    3:0.44
    4:0.02
    5:0.08
    6:0.02
    7:0.05
    8:0.06
    9:0.01
    10:0.07
    11:0.02
    Negative Logits
     clich
    -2.19
    ifles
    -2.19
     frying
    -2.16
     bombs
    -2.14
     fools
    -2.13
     sacrifices
    -2.12
     selfies
    -2.10
     bottles
    -2.10
     scraps
    -2.10
     slogans
    -2.08
    POSITIVE LOGITS
     coordinator
    3.46
     director
    3.36
    director
    3.26
     curator
    3.12
     advisor
    3.07
     adviser
    3.00
     consultant
    2.99
     expert
    2.95
     administrator
    2.94
     Coordinator
    2.92
    Activations Density 0.526%

    No Known Activations