© 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. 246
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names 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
    0:0.05
    1:0.03
    2:0.04
    3:0.05
    4:0.04
    5:0.04
    6:0.11
    7:0.03
    8:0.04
    9:0.49
    10:0.02
    11:0.02
    Negative Logits
    oux
    -4.03
     Barth
    -3.59
     Skydragon
    -3.34
     typew
    -3.25
    zo
    -3.25
     decon
    -3.23
    dayName
    -3.21
     broker
    -3.18
    �
    -3.17
    asters
    -3.11
    POSITIVE LOGITS
    il
    6.56
    IL
    6.32
    ils
    5.70
    iled
    5.02
    iling
    4.98
     Hil
    4.90
    ILS
    4.90
     Il
    4.85
    iles
    4.79
    Gil
    4.79
    Activations Density 0.008%

    No Known Activations