© 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. 10976
    Prev
    Next
    INDEX
    Explanations

    references to the "Broken Universe" concept

    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
    0:0.07
    1:0.10
    2:0.04
    3:0.07
    4:0.06
    5:0.05
    6:0.22
    7:0.03
    8:0.05
    9:0.18
    10:0.03
    11:0.03
    Negative Logits
     Sachs
    -3.41
     HRC
    -3.27
     jog
    -3.12
    displayText
    -3.08
     Schiff
    -3.07
     heel
    -3.06
     Chaff
    -2.99
     Jarrett
    -2.98
    Skill
    -2.92
     Kemp
    -2.91
    POSITIVE LOGITS
     universe
    6.02
     Universe
    5.99
     universes
    5.44
     cosmos
    4.85
     Cosmos
    4.37
     Univers
    4.26
    iverse
    4.13
     galaxies
    3.98
     galaxy
    3.71
     afterlife
    3.70
    Activations Density 0.002%

    No Known Activations