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

    Neuronpedia

    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. 10929
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to significant events or endorsements in a political context

    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
    0:0.08
    1:0.02
    2:0.04
    3:0.03
    4:0.04
    5:0.03
    6:0.28
    7:0.05
    8:0.07
    9:0.27
    10:0.01
    11:0.03
    Negative Logits
     Alc
    -3.69
     LEG
    -3.61
     wing
    -3.54
     sac
    -3.54
     cad
    -3.48
    Emb
    -3.46
     hangar
    -3.40
     Spac
    -3.38
    Wing
    -3.38
     helic
    -3.36
    POSITIVE LOGITS
     Murray
    11.50
    Murray
    11.16
    mine
    4.37
    Mine
    4.26
     Maria
    4.25
     Mining
    4.05
     Rooney
    4.05
     Ramirez
    3.99
     Ramsay
    3.97
     miners
    3.91
    Activations Density 0.008%

    No Known Activations