© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11848
    Prev
    Next
    INDEX
    Explanations

    contextual references to political events and their 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
    0:0.06
    1:0.07
    2:0.05
    3:0.19
    4:0.05
    5:0.06
    6:0.15
    7:0.06
    8:0.03
    9:0.17
    10:0.03
    11:0.04
    Negative Logits
    Asset
    -2.67
    HUD
    -2.63
     Mason
    -2.53
     Reneg
    -2.50
     Lauder
    -2.47
     Asset
    -2.39
     Kessler
    -2.38
     Flag
    -2.30
     Lie
    -2.25
     Minion
    -2.24
    POSITIVE LOGITS
     Tian
    2.66
     pope
    2.61
     canonical
    2.46
    yon
    2.41
    daq
    2.38
     pap
    2.38
    kus
    2.33
    icans
    2.31
    english
    2.30
    quished
    2.27
    Activations Density 0.004%

    No Known Activations