© 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. 43042
    Prev
    Next
    INDEX
    Explanations

    occurrences of location-related prepositions

    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
    0:0.02
    1:0.03
    2:0.09
    3:0.05
    4:0.12
    5:0.03
    6:0.08
    7:0.19
    8:0.04
    9:0.05
    10:0.14
    11:0.12
    Negative Logits
     handling
    -1.30
     ana
    -1.27
     renaissance
    -1.22
     adm
    -1.21
     juices
    -1.19
     dipping
    -1.18
     exorc
    -1.17
     recount
    -1.14
     parted
    -1.12
     Quit
    -1.11
    POSITIVE LOGITS
    Site
    1.50
    Sit
    1.39
    ilaterally
    1.37
    clude
    1.37
    site
    1.35
     locations
    1.35
    sites
    1.33
    holes
    1.33
     sites
    1.32
    cellaneous
    1.32
    Activations Density 0.000%

    No Known Activations