© 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. 10-ATT-KK
    11. 11985
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss proposals and their implications

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.04
    2:0.04
    3:0.05
    4:0.13
    5:0.03
    6:0.22
    7:0.21
    8:0.01
    9:0.03
    10:0.03
    11:0.12
    Negative Logits
     tremend
    -2.77
     COUR
    -2.61
     unmarked
    -2.50
    reet
    -2.46
    trial
    -2.46
     bliss
    -2.40
     routines
    -2.32
     unequ
    -2.19
     tutorials
    -2.19
     Painter
    -2.16
    POSITIVE LOGITS
     proposal
    5.67
     proposals
    5.61
     proposing
    4.44
     propose
    4.30
     proposed
    4.26
     proposes
    4.06
     propos
    3.30
     suggestion
    3.06
     suggestions
    3.04
     draft
    3.02
    Activations Density 0.166%

    No Known Activations