© 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. 10994
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing ideas and understanding

    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
    2:0.05
    3:0.12
    4:0.04
    5:0.27
    6:0.03
    7:0.06
    8:0.03
    9:0.03
    10:0.20
    11:0.03
    Negative Logits
     Ingredients
    -3.06
    Ingredients
    -2.78
     mistakenly
    -2.67
     (@
    -2.57
     incorrectly
    -2.57
    Recipe
    -2.55
    OTUS
    -2.45
     falsely
    -2.33
     wrongly
    -2.33
    ](
    -2.33
    POSITIVE LOGITS
     consolidation
    3.06
     decentral
    3.04
    trak
    3.00
     clust
    2.92
    owship
    2.83
     separat
    2.81
     unrestricted
    2.77
    anton
    2.74
    izons
    2.70
     aggregation
    2.63
    Activations Density 0.001%

    No Known Activations