© 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. 47097
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to positional prepositions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.05
    2:0.10
    3:0.03
    4:0.10
    5:0.15
    6:0.11
    7:0.09
    8:0.12
    9:0.03
    10:0.04
    11:0.09
    Negative Logits
    cius
    -1.74
    ano
    -1.34
    toe
    -1.30
     halfway
    -1.27
     FIRST
    -1.26
     digitally
    -1.24
    cientious
    -1.23
     76
    -1.22
     Doctors
    -1.21
    iage
    -1.21
    POSITIVE LOGITS
    etheless
    2.19
    soType
    1.77
     conclud
    1.63
    使
    1.62
    龍喚士
    1.58
    姫
    1.47
     behavi
    1.47
    dayName
    1.46
    ORPG
    1.46
    depending
    1.44
    Activations Density 0.000%

    No Known Activations