© 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. 2321
    Prev
    Next
    INDEX
    Explanations

    references to significant events and contexts associated with societal issues

    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
    1:0.04
    2:0.28
    3:0.06
    4:0.11
    5:0.03
    6:0.07
    7:0.09
    8:0.05
    9:0.04
    10:0.08
    11:0.07
    Negative Logits
     Kinnikuman
    -1.92
     Related
    -1.62
     Lots
    -1.60
     respective
    -1.60
     Detail
    -1.57
    adders
    -1.54
    gio
    -1.54
    artments
    -1.52
    conserv
    -1.45
    oun
    -1.44
    POSITIVE LOGITS
    DH
    1.75
     Imran
    1.64
     appet
    1.60
    レ
    1.56
    ンジ
    1.52
     RSA
    1.50
    alker
    1.50
    UGH
    1.47
     Cham
    1.47
     itch
    1.46
    Activations Density 0.001%

    No Known Activations