© 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. 8283
    Prev
    Next
    INDEX
    Explanations

    themes related to animal welfare and dogs, particularly concerning care and management of pets

    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
    0:0.40
    1:0.04
    2:0.04
    3:0.04
    4:0.07
    5:0.03
    6:0.06
    7:0.07
    8:0.02
    9:0.05
    10:0.07
    11:0.07
    Negative Logits
     Hassan
    -4.40
     Bosh
    -4.12
     Stephenson
    -3.88
     Hasan
    -3.52
     Hawai
    -3.50
     piracy
    -3.49
     Mahm
    -3.46
     eru
    -3.36
     Ragnarok
    -3.32
     Volcano
    -3.27
    POSITIVE LOGITS
     dogs
    9.17
     puppies
    8.80
     dog
    8.67
     canine
    8.61
    Dog
    8.49
     puppy
    8.47
     Dogs
    8.39
    dog
    7.69
     pets
    7.68
    dogs
    7.53
    Activations Density 0.427%

    No Known Activations