© 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. 3470
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate formal statements or significant events

    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
    2:0.06
    3:0.03
    4:0.06
    5:0.05
    6:0.21
    7:0.06
    8:0.08
    9:0.23
    10:0.02
    11:0.05
    Negative Logits
     Flor
    -4.07
    Flor
    -3.95
     foreclosure
    -3.52
     Augusta
    -3.50
     bay
    -3.50
     Bent
    -3.44
     Merrill
    -3.44
    atus
    -3.42
     Bere
    -3.36
     Bree
    -3.33
    POSITIVE LOGITS
     Singh
    9.83
    Sing
    8.14
     Sing
    4.98
     Sikh
    4.79
     Sik
    4.58
     Neh
    4.45
    sing
    4.45
     sing
    4.33
     Ride
    3.97
     Tag
    3.87
    Activations Density 0.003%

    No Known Activations