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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14488
    Prev
    Next
    INDEX
    Explanations

    concepts related to familial relationships and emotional ties

    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
    0:0.12
    1:0.22
    2:0.06
    3:0.03
    4:0.03
    5:0.02
    6:0.07
    7:0.12
    8:0.03
    9:0.03
    10:0.14
    11:0.07
    Negative Logits
     Griffith
    -2.46
     Bee
    -2.31
     bee
    -2.31
     eng
    -2.30
    Advanced
    -2.24
     Ste
    -2.22
     hydra
    -2.21
     beetle
    -2.20
    �
    -2.19
     ENG
    -2.17
    POSITIVE LOGITS
     Sole
    7.21
    sole
    4.50
    Sol
    4.04
    ole
    3.60
     Mole
    3.58
    sol
    3.56
     Sol
    3.34
     sol
    3.29
     sole
    3.17
    oles
    2.91
    Activations Density 0.001%

    No Known Activations