© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 4928
    Prev
    Next
    INDEX
    Explanations

    actions related to clicking and selecting options or elements on a user interface

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.03
    2:0.09
    3:0.10
    4:0.20
    5:0.03
    6:0.06
    7:0.11
    8:0.04
    9:0.04
    10:0.11
    11:0.10
    Negative Logits
    lycer
    -1.34
    LOD
    -1.25
    CONCLUS
    -1.25
    direction
    -1.24
    Els
    -1.24
     conclud
    -1.24
    Translation
    -1.20
     extraord
    -1.20
     endorsements
    -1.19
     Conclusion
    -1.18
    POSITIVE LOGITS
     offending
    1.48
     suspects
    1.36
     accuser
    1.30
     Pastebin
    1.23
     statue
    1.18
     commits
    1.18
     suspected
    1.17
    prison
    1.16
     ledger
    1.15
     awhile
    1.15
    Activations Density 0.001%

    No Known Activations