© 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. 24753
    Prev
    Next
    INDEX
    Explanations

    technical details and features related to equipment and organization within the context of systems and events

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.03
    1:0.01
    2:0.16
    3:0.13
    4:0.07
    5:0.05
    6:0.02
    7:0.05
    8:0.09
    9:0.10
    10:0.15
    11:0.09
    Negative Logits
     fundamentally
    -1.43
     necessarily
    -1.19
    ynthesis
    -1.17
    imester
    -1.15
     unilaterally
    -1.14
     inherently
    -1.14
    �
    -1.12
    wrong
    -1.11
     Cassidy
    -1.08
    inventoryQuantity
    -1.08
    POSITIVE LOGITS
    jas
    1.11
     Credits
    1.08
     cafes
    1.06
    ibli
    1.04
     headsets
    1.04
    cellaneous
    1.03
     calendars
    1.02
     snacks
    1.02
    Optional
    1.01
    ici
    1.01
    Activations Density 0.629%

    No Known Activations