© 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. 9-ATT-KK
    6. 21280
    Prev
    Next
    INDEX
    Explanations

    terms related to dog breeds and their popularity or sentiment among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.19
    1:0.04
    2:0.19
    3:0.10
    4:0.05
    5:0.05
    6:0.09
    7:0.06
    8:0.05
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
     Ghostbusters
    -3.00
    NetMessage
    -2.99
     eru
    -2.99
    rawled
    -2.76
     Volcano
    -2.75
     volcano
    -2.69
     eruption
    -2.67
     blackout
    -2.63
    desktop
    -2.60
     Flan
    -2.58
    POSITIVE LOGITS
     breed
    6.46
     breeding
    6.01
     bred
    5.81
     breeds
    5.69
     Breed
    5.67
    bred
    5.18
    breeding
    4.94
     pedigree
    4.89
     puppy
    4.65
     puppies
    4.51
    Activations Density 0.009%

    No Known Activations