© 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. 7007
    Prev
    Next
    INDEX
    Explanations

    the structure of conditional phrases involving the word "were" and its implications

    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
    1:0.01
    2:0.09
    3:0.11
    4:0.07
    5:0.05
    6:0.07
    7:0.04
    8:0.04
    9:0.05
    10:0.09
    11:0.29
    Negative Logits
    Font
    -1.75
     Bach
    -1.67
     Toledo
    -1.67
     Hosp
    -1.59
     Libraries
    -1.58
    Chelsea
    -1.56
    Alabama
    -1.54
     stadiums
    -1.51
     Atmosp
    -1.50
    Async
    -1.50
    POSITIVE LOGITS
     defect
    1.79
    unker
    1.72
     buyer
    1.63
     stalk
    1.61
    zilla
    1.59
     testers
    1.58
     hatched
    1.56
    eeper
    1.53
     penetration
    1.52
     hatch
    1.52
    Activations Density 0.014%

    No Known Activations