© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 12111
    Prev
    Next
    INDEX
    Explanations

    locations, specifically those that evoke strong imagery or emotional responses

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.03
    3:0.04
    4:0.07
    5:0.06
    6:0.05
    7:0.06
    8:0.02
    9:0.12
    10:0.02
    11:0.42
    Negative Logits
     agendas
    -2.44
     incumb
    -2.37
     priorities
    -2.32
     contributors
    -2.32
     stakeholders
    -2.30
     constituents
    -2.27
     Topics
    -2.26
     agenda
    -2.25
     recipients
    -2.19
    agonist
    -2.17
    POSITIVE LOGITS
     bathroom
    3.37
     restroom
    3.34
     alley
    3.25
     baths
    3.06
     bath
    3.02
     bathrooms
    3.01
     hallway
    2.99
     restrooms
    2.99
     courtyard
    2.99
     garage
    2.91
    Activations Density 0.297%

    No Known Activations