© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 14338
    Prev
    Next
    INDEX
    Explanations

    references to balance and its various contexts, particularly in social and economic 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
    0:0.38
    1:0.03
    2:0.13
    3:0.07
    4:0.03
    5:0.05
    6:0.03
    7:0.04
    8:0.04
    9:0.03
    10:0.11
    11:0.03
    Negative Logits
     spores
    -3.00
    spons
    -2.49
     payload
    -2.32
     ger
    -2.31
     reuse
    -2.30
     cache
    -2.23
     advertise
    -2.21
     keynote
    -2.16
     descriptor
    -2.15
     caches
    -2.15
    POSITIVE LOGITS
     tilted
    3.41
    balanced
    3.14
     tipped
    3.09
     "$:/
    3.05
     Balance
    2.91
    balance
    2.79
     tilt
    2.75
     adjustment
    2.70
     adjustments
    2.65
     balances
    2.65
    Activations Density 0.021%

    No Known Activations