© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21403
    Prev
    Next
    INDEX
    Explanations

    references to Pokémon video games, characters, and gameplay mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.06
    2:0.16
    3:0.07
    4:0.09
    5:0.08
    6:0.04
    7:0.03
    8:0.05
    9:0.19
    10:0.08
    11:0.04
    Negative Logits
    ebus
    -1.38
    displayText
    -1.28
    Wil
    -1.27
    ofi
    -1.23
    nel
    -1.23
    beck
    -1.20
     departures
    -1.20
    berger
    -1.20
     arrang
    -1.19
    idious
    -1.19
    POSITIVE LOGITS
     Slug
    1.45
     Meow
    1.32
    ombat
    1.31
    Pokemon
    1.24
     Madagascar
    1.23
     Silent
    1.23
     Frozen
    1.22
    opter
    1.21
    ™
    1.21
     Doodle
    1.20
    Activations Density 0.013%

    No Known Activations