© 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. 33230
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating purpose or direction

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.12
    3:0.06
    4:0.24
    5:0.02
    6:0.03
    7:0.24
    8:0.03
    9:0.03
    10:0.06
    11:0.12
    Negative Logits
     Credits
    -1.84
     compensate
    -1.68
     unlocked
    -1.65
     rewards
    -1.64
     Reward
    -1.64
    ヘ
    -1.60
     teasp
    -1.60
    Reward
    -1.59
     upkeep
    -1.58
     compensated
    -1.56
    POSITIVE LOGITS
     dissenting
    1.97
     dissent
    1.86
     paradox
    1.72
     phenomena
    1.56
     hypothesis
    1.55
    ideshow
    1.53
    ively
    1.52
     fallacy
    1.50
     epidem
    1.44
     argument
    1.42
    Activations Density 0.004%

    No Known Activations