© 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. 43764
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" and related prepositions and conjunctions

    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
    1:0.01
    2:0.17
    3:0.05
    4:0.17
    5:0.03
    6:0.05
    7:0.13
    8:0.05
    9:0.04
    10:0.11
    11:0.11
    Negative Logits
     senses
    -1.30
    missive
    -1.25
    etti
    -1.25
     cries
    -1.25
     faint
    -1.23
    abet
    -1.22
    ileged
    -1.22
     disappoint
    -1.21
     flavours
    -1.21
    iable
    -1.20
    POSITIVE LOGITS
    irlf
    1.55
     Pengu
    1.45
     Nau
    1.41
     Beacon
    1.37
     Jericho
    1.37
     Wiz
    1.35
    uggest
    1.32
     Avalon
    1.31
    BM
    1.30
    nect
    1.30
    Activations Density 0.056%

    No Known Activations