© 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. 2-ATT-KK
    11. 14821
    Prev
    Next
    INDEX
    Explanations

    terms related to light and wave properties, such as vibrating, perpendicular, polarization, and holograms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.11
    2:0.05
    3:0.06
    4:0.03
    5:0.07
    6:0.07
    7:0.10
    8:0.05
    9:0.13
    10:0.14
    11:0.06
    Negative Logits
     commissions
    -1.45
     fundraising
    -1.44
     stewards
    -1.42
     fundra
    -1.41
     vets
    -1.39
    atre
    -1.37
     ambassador
    -1.35
     heartfelt
    -1.33
     ambassadors
    -1.33
     advoc
    -1.33
    POSITIVE LOGITS
     equilibrium
    2.03
     electrons
    1.97
     atoms
    1.91
     coefficients
    1.90
     computed
    1.85
     \(\
    1.73
     oscill
    1.72
     Δ
    1.71
     geometry
    1.69
     equations
    1.69
    Activations Density 0.294%

    No Known Activations