© 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. 21498
    Prev
    Next
    INDEX
    Explanations

    statements involving claims or assertions about various subjects within the text

    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
    1:0.02
    2:0.08
    3:0.31
    4:0.03
    5:0.16
    6:0.02
    7:0.11
    8:0.03
    9:0.02
    10:0.11
    11:0.01
    Negative Logits
     Krugman
    -2.00
    Soviet
    -2.00
     conspir
    -1.96
    Govern
    -1.95
     neocons
    -1.94
     Stalin
    -1.93
     administ
    -1.92
     Socialist
    -1.90
     triumphant
    -1.88
     Britann
    -1.87
    POSITIVE LOGITS
     applications
    1.96
     delays
    1.94
     uses
    1.93
     improperly
    1.88
     detects
    1.83
     tests
    1.82
     refunds
    1.81
     measurements
    1.80
     detected
    1.79
     functionality
    1.78
    Activations Density 0.340%

    No Known Activations