© 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. 5-ATT-KK
    11. 35558
    Prev
    Next
    INDEX
    Explanations

    contexts involving chaos and turmoil

    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
    0:0.01
    1:0.03
    2:0.07
    3:0.05
    4:0.11
    5:0.02
    6:0.03
    7:0.38
    8:0.04
    9:0.03
    10:0.10
    11:0.09
    Negative Logits
     Attribution
    -1.89
    FINE
    -1.57
    heit
    -1.49
    arma
    -1.47
    axter
    -1.47
    onyms
    -1.44
    quickShipAvailable
    -1.44
    fter
    -1.43
    tek
    -1.38
    ffer
    -1.38
    POSITIVE LOGITS
     revolving
    1.70
     affairs
    1.68
     squats
    1.64
     palace
    1.58
     barracks
    1.50
     menstru
    1.49
     assembly
    1.47
     battles
    1.45
     wars
    1.43
     unions
    1.43
    Activations Density 0.012%

    No Known Activations