© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 47233
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs indicating future actions or conditions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.14
    1:0.17
    2:0.06
    3:0.06
    4:0.05
    5:0.11
    6:0.06
    7:0.04
    8:0.10
    9:0.06
    10:0.06
    11:0.06
    Negative Logits
     Ober
    -1.87
     Kut
    -1.84
     Tot
    -1.83
     CK
    -1.83
     Kap
    -1.79
     Method
    -1.76
     Kop
    -1.75
     Fu
    -1.65
     Ti
    -1.65
     Pry
    -1.62
    POSITIVE LOGITS
    entimes
    1.85
     deaf
    1.84
     starve
    1.82
     suck
    1.81
     freezes
    1.75
    untu
    1.74
    lict
    1.72
    ousy
    1.70
     depended
    1.70
    licts
    1.68
    Activations Density 0.000%

    No Known Activations