© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14334
    Prev
    Next
    INDEX
    Explanations

    words related to family relationships and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.07
    2:0.16
    3:0.04
    4:0.05
    5:0.02
    6:0.05
    7:0.28
    8:0.02
    9:0.03
    10:0.06
    11:0.09
    Negative Logits
    heads
    -2.37
    wings
    -2.16
    bending
    -2.16
     Attacks
    -2.09
     Refugees
    -2.04
    iders
    -1.97
     Characters
    -1.96
    Berry
    -1.94
     Islanders
    -1.91
     riders
    -1.85
    POSITIVE LOGITS
     vas
    2.10
    emn
    2.10
    ufact
    2.02
     execut
    1.99
    cler
    1.96
     Chem
    1.94
     Pharm
    1.92
     proc
    1.90
    orget
    1.89
    chem
    1.88
    Activations Density 0.014%

    No Known Activations