© 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. 18897
    Prev
    Next
    INDEX
    Explanations

    references to media outlets or publications

    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
    0:0.15
    1:0.01
    2:0.04
    3:0.27
    4:0.04
    5:0.09
    6:0.03
    7:0.04
    8:0.05
    9:0.03
    10:0.18
    11:0.03
    Negative Logits
     registrations
    -2.40
     preferential
    -2.35
     registration
    -2.17
     substitution
    -2.17
     requested
    -2.13
     satisfactory
    -2.11
     receipts
    -2.06
     certificates
    -2.03
     exceptions
    -2.00
     certificate
    -2.00
    POSITIVE LOGITS
    izons
    2.52
    Truth
    2.25
    aminer
    2.20
    story
    2.17
    istan
    2.14
    yssey
    2.12
    yond
    2.09
    nir
    2.06
    stories
    2.03
    inion
    2.02
    Activations Density 0.005%

    No Known Activations