© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 13903
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict or struggles in relationships

    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
    0:0.11
    1:0.32
    2:0.09
    3:0.04
    4:0.03
    5:0.02
    6:0.07
    7:0.07
    8:0.01
    9:0.03
    10:0.11
    11:0.04
    Negative Logits
    undai
    -2.86
    Aust
    -2.66
     Ic
    -2.64
    istas
    -2.54
     Nicaragua
    -2.47
    ista
    -2.44
     pes
    -2.43
     Laur
    -2.42
     NRL
    -2.39
    ilst
    -2.37
    POSITIVE LOGITS
    Gray
    9.45
     Gray
    8.85
     gray
    7.52
    gray
    7.28
     grey
    6.43
    Grey
    5.83
     Grey
    5.62
    grey
    5.51
     black
    4.13
     brown
    3.75
    Activations Density 0.016%

    No Known Activations