© 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. 10136
    Prev
    Next
    INDEX
    Explanations

    instances of comments or remarks that indicate opinions or subjective expressions

    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
    1:0.02
    2:0.08
    3:0.04
    4:0.18
    5:0.03
    6:0.27
    7:0.15
    8:0.03
    9:0.02
    10:0.06
    11:0.06
    Negative Logits
    QL
    -1.29
    innacle
    -1.29
    itals
    -1.25
    avorite
    -1.23
    incial
    -1.23
    icion
    -1.21
    xtap
    -1.19
    imity
    -1.19
    mega
    -1.19
     Beyond
    -1.19
    POSITIVE LOGITS
     footprints
    1.39
     reluct
    1.34
     drawer
    1.29
     judgement
    1.29
     Ruk
    1.25
     trenches
    1.25
     Lumpur
    1.24
     wreckage
    1.22
     stranded
    1.21
     unanim
    1.21
    Activations Density 0.032%

    No Known Activations