© 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. 23278
    Prev
    Next
    INDEX
    Explanations

    concepts related to learning and education

    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
    1:0.03
    2:0.03
    3:0.04
    4:0.09
    5:0.04
    6:0.03
    7:0.05
    8:0.02
    9:0.11
    10:0.02
    11:0.44
    Negative Logits
    osponsors
    -2.52
    orescence
    -2.36
    orescent
    -2.31
     billboards
    -2.27
    azo
    -2.26
     billboard
    -2.20
    appointed
    -2.16
    vertisement
    -2.16
     commenter
    -2.15
     advertisements
    -2.08
    POSITIVE LOGITS
     tricks
    3.99
     skills
    3.66
     basics
    3.46
     techniques
    3.24
     fundamentals
    3.20
     secrets
    3.14
    iquette
    3.14
     Technique
    3.06
     knowledge
    3.03
     learnt
    2.99
    Activations Density 0.110%

    No Known Activations