© 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. 44612
    Prev
    Next
    INDEX
    Explanations

    instances of people or entities that trigger events or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.02
    2:0.12
    3:0.30
    4:0.13
    5:0.03
    6:0.03
    7:0.07
    8:0.05
    9:0.04
    10:0.08
    11:0.05
    Negative Logits
     insofar
    -1.76
    responsible
    -1.56
     MacArthur
    -1.50
     Ober
    -1.49
    udos
    -1.41
     Coulter
    -1.41
    ‎
    -1.38
     Rah
    -1.38
    bourg
    -1.37
     Fuller
    -1.37
    POSITIVE LOGITS
    uddenly
    2.13
     slightest
    1.95
    pires
    1.62
     suddenly
    1.59
    heit
    1.56
    ggles
    1.54
    ymes
    1.52
    pa
    1.51
     or
    1.49
    apses
    1.45
    Activations Density 0.050%

    No Known Activations