© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 8639
    Prev
    Next
    INDEX
    Explanations

    passive voice constructions or phrases indicating passive actions

    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
    0:0.16
    1:0.39
    2:0.02
    3:0.02
    4:0.02
    5:0.14
    6:0.02
    7:0.02
    8:0.05
    9:0.05
    10:0.04
    11:0.03
    Negative Logits
    oké
    -2.09
    rollers
    -1.91
    aci
    -1.81
    onom
    -1.81
    plant
    -1.79
    bec
    -1.78
    attach
    -1.73
    wash
    -1.69
    fur
    -1.68
    omi
    -1.67
    POSITIVE LOGITS
     15
    2.67
     28
    2.64
     14
    2.62
     35
    2.61
     36
    2.59
     5
    2.58
     17
    2.55
     6
    2.55
     52
    2.54
     7
    2.54
    Activations Density 0.143%

    No Known Activations