© 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. 10-ATT-KK
    11. 7524
    Prev
    Next
    INDEX
    Explanations

    aspects related to animals, particularly pets and their care

    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
    0:0.15
    1:0.09
    2:0.06
    3:0.06
    4:0.06
    5:0.03
    6:0.16
    7:0.12
    8:0.02
    9:0.04
    10:0.10
    11:0.06
    Negative Logits
    ufact
    -3.64
     Korra
    -2.81
     Kub
    -2.78
    packing
    -2.71
     Courier
    -2.68
     cu
    -2.59
    effects
    -2.43
    ć
    -2.43
     Duc
    -2.41
    Wars
    -2.40
    POSITIVE LOGITS
     hedge
    6.87
     Hedge
    5.80
     hed
    4.79
     Goldman
    3.72
    edge
    3.55
     Advis
    3.46
     Barclays
    3.31
     Cantor
    3.13
     Investment
    3.09
     Adviser
    3.05
    Activations Density 0.008%

    No Known Activations