© 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. 5-ATT-KK
    6. 18818
    Prev
    Next
    INDEX
    Explanations

    references to the European Union and related concepts like exiting conditions

    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
    0:0.03
    1:0.02
    2:0.06
    3:0.05
    4:0.17
    5:0.04
    6:0.05
    7:0.31
    8:0.03
    9:0.04
    10:0.08
    11:0.07
    Negative Logits
    tips
    -1.83
    tip
    -1.72
    antage
    -1.62
     strengths
    -1.61
     counterparts
    -1.43
    PDATED
    -1.42
    soType
    -1.39
     shaped
    -1.38
     underpin
    -1.38
    andise
    -1.37
    POSITIVE LOGITS
     altogether
    1.77
     prematurely
    1.70
    BuyableInstoreAndOnline
    1.65
     limbo
    1.57
     abruptly
    1.35
     hiber
    1.35
     Leaving
    1.35
     captivity
    1.35
     boredom
    1.31
     Corpse
    1.28
    Activations Density 0.000%

    No Known Activations