© 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. 16909
    Prev
    Next
    INDEX
    Explanations

    references to motor activity and its correlation with emotional states

    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
    0:0.04
    1:0.01
    2:0.05
    3:0.09
    4:0.05
    5:0.07
    6:0.03
    7:0.05
    8:0.04
    9:0.12
    10:0.24
    11:0.16
    Negative Logits
     thous
    -1.31
    chwitz
    -1.21
    thora
    -1.20
     Bung
    -1.08
    ylum
    -1.07
     miracle
    -1.07
    DragonMagazine
    -1.05
    ratulations
    -1.05
    Reloaded
    -1.03
    artisan
    -1.03
    POSITIVE LOGITS
     behaviors
    1.31
     initiating
    1.27
     interactions
    1.26
     interpersonal
    1.24
     mediated
    1.24
     versus
    1.21
     stimuli
    1.17
     interact
    1.14
     interacting
    1.14
     engaging
    1.14
    Activations Density 0.712%

    No Known Activations