© 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. 9-ATT-KK
    11. 5745
    Prev
    Next
    INDEX
    Explanations

    phrases that involve the concept of value or worth related to various subjects

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.07
    1:0.04
    2:0.06
    3:0.22
    4:0.03
    5:0.04
    6:0.03
    7:0.05
    8:0.05
    9:0.03
    10:0.27
    11:0.05
    Negative Logits
    ocide
    -2.47
     implanted
    -2.31
    apa
    -2.16
     outlawed
    -2.13
     implicated
    -2.11
     patents
    -2.11
     genes
    -2.10
    idas
    -2.09
     rescind
    -2.08
     malice
    -2.07
    POSITIVE LOGITS
     lively
    3.01
    Reviewer
    2.96
     enjoyable
    2.77
     slideshow
    2.69
     scenes
    2.63
     festive
    2.61
     fascinating
    2.57
     entertaining
    2.50
     memorable
    2.48
     contrasts
    2.45
    Activations Density 0.006%

    No Known Activations