© 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. 8836
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs, particularly 'to' followed by action-related terms

    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
    0:0.02
    1:0.01
    2:0.13
    3:0.07
    4:0.06
    5:0.03
    6:0.07
    7:0.29
    8:0.07
    9:0.03
    10:0.07
    11:0.09
    Negative Logits
    cludes
    -1.59
    etermined
    -1.40
    ipel
    -1.38
    anwhile
    -1.35
    aneous
    -1.34
    bris
    -1.34
    nown
    -1.34
     omission
    -1.31
     Includes
    -1.29
    edly
    -1.28
    POSITIVE LOGITS
    エ
    1.36
     sew
    1.35
     levers
    1.34
    usb
    1.34
     rgb
    1.32
     leptin
    1.32
     hous
    1.28
    yles
    1.25
     wrestling
    1.23
     thumbs
    1.22
    Activations Density 0.006%

    No Known Activations