© 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. 45779
    Prev
    Next
    INDEX
    Explanations

    modal verbs and phrases that express obligation or necessity

    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
    0:0.17
    1:0.32
    2:0.04
    3:0.03
    4:0.03
    5:0.13
    6:0.03
    7:0.03
    8:0.07
    9:0.04
    10:0.03
    11:0.03
    Negative Logits
     Leilan
    -2.05
    owship
    -1.87
    nesota
    -1.82
     corpus
    -1.75
    lements
    -1.72
    \/\/
    -1.71
     LU
    -1.70
    oran
    -1.67
     autonom
    -1.66
    ERG
    -1.66
    POSITIVE LOGITS
    Say
    2.37
    Said
    2.26
    Shot
    2.25
     say
    2.15
    Msg
    2.06
    Winged
    2.04
    say
    1.91
     Says
    1.86
     Saying
    1.86
    Point
    1.84
    Activations Density 0.005%

    No Known Activations