© 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. 9900
    Prev
    Next
    INDEX
    Explanations

    conditional statements reflecting past decisions or hypothetical scenarios

    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
    0:0.03
    1:0.03
    2:0.04
    3:0.22
    4:0.02
    5:0.06
    6:0.02
    7:0.08
    8:0.03
    9:0.02
    10:0.37
    11:0.03
    Negative Logits
    /.
    -2.14
    roups
    -2.00
    sections
    -1.98
    asca
    -1.96
    sometimes
    -1.95
    )</
    -1.91
    includes
    -1.89
    Related
    -1.89
    und
    -1.87
     Highlights
    -1.85
    POSITIVE LOGITS
     anywhere
    2.06
     honest
    2.04
     sooner
    2.03
     anymore
    2.01
     comparable
    1.99
     anyway
    1.98
     ANY
    1.97
    Instead
    1.92
     probability
    1.90
     tomorrow
    1.84
    Activations Density 0.146%

    No Known Activations