© 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. 24759
    Prev
    Next
    INDEX
    Explanations

    common articles and prepositions used in various contexts

    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
    0:0.03
    1:0.01
    2:0.11
    3:0.06
    4:0.13
    5:0.02
    6:0.24
    7:0.11
    8:0.04
    9:0.04
    10:0.08
    11:0.07
    Negative Logits
     Cham
    -1.34
     EPS
    -1.22
     Cha
    -1.18
    ghan
    -1.13
     Channel
    -1.11
     effective
    -1.10
     Sa
    -1.10
       
    -1.09
     PATH
    -1.08
     Seventh
    -1.06
    POSITIVE LOGITS
    odder
    1.60
    pedia
    1.52
    nown
    1.35
    details
    1.35
    Info
    1.31
    ucket
    1.31
    otos
    1.28
    oodoo
    1.28
    abilia
    1.28
    oots
    1.26
    Activations Density 0.005%

    No Known Activations