© 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. 5-ATT-KK
    11. 36741
    Prev
    Next
    INDEX
    Explanations

    references to specific characters, names, and keywords related to Pokémon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.38
    2:0.03
    3:0.04
    4:0.03
    5:0.21
    6:0.04
    7:0.02
    8:0.05
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
     Subway
    -2.09
     Socialism
    -1.94
     socialists
    -1.78
     Sky
    -1.75
     Torah
    -1.72
     sky
    -1.71
     Esk
    -1.69
     Judaism
    -1.66
     HF
    -1.65
     swast
    -1.63
    POSITIVE LOGITS
    ell
    2.54
    ill
    2.52
    ILL
    2.52
    rill
    2.38
    ELL
    2.30
    eller
    2.29
    illation
    2.20
    iller
    2.18
    ril
    2.11
    ll
    2.07
    Activations Density 0.002%

    No Known Activations