© 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. 38401
    Prev
    Next
    INDEX
    Explanations

    positive phrases related to enjoyment and appreciation

    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
    0:0.02
    1:0.01
    2:0.05
    3:0.09
    4:0.18
    5:0.03
    6:0.08
    7:0.26
    8:0.04
    9:0.03
    10:0.09
    11:0.06
    Negative Logits
    yout
    -1.68
     HOW
    -1.60
    ento
    -1.52
    onto
    -1.48
     INTO
    -1.47
    iframe
    -1.44
     Cree
    -1.43
     QUEST
    -1.35
     newsp
    -1.34
    ffield
    -1.34
    POSITIVE LOGITS
     advantages
    1.91
     turnover
    1.73
    capacity
    1.73
    ulatory
    1.57
     exemptions
    1.56
     favourable
    1.56
    orbit
    1.55
     privileges
    1.53
     possession
    1.52
     occupancy
    1.51
    Activations Density 0.007%

    No Known Activations