© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 35843
    Prev
    Next
    INDEX
    Explanations

    references to bike races and the Giro event specifically

    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
    0:0.02
    1:0.01
    2:0.07
    3:0.06
    4:0.05
    5:0.05
    6:0.05
    7:0.04
    8:0.04
    9:0.09
    10:0.42
    11:0.07
    Negative Logits
     Bungie
    -2.03
     Jehovah
    -2.00
    Spell
    -1.92
     Torment
    -1.90
     Abilities
    -1.89
     Cortana
    -1.87
     Harden
    -1.86
     Malfoy
    -1.86
     Bahá
    -1.85
     Atari
    -1.81
    POSITIVE LOGITS
     contenders
    2.11
     organizers
    2.09
     organisers
    2.09
    anwhile
    2.06
     staging
    2.02
    uesday
    1.90
     convoy
    1.88
     summit
    1.86
     mosqu
    1.85
    iners
    1.83
    Activations Density 0.000%

    No Known Activations