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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 27646
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "a" and phrases that demonstrate repetition or similarity

    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
    0:0.05
    1:0.03
    2:0.14
    3:0.05
    4:0.08
    5:0.04
    6:0.32
    7:0.03
    8:0.06
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
    advertisement
    -1.61
    Fin
    -1.36
    Access
    -1.34
    MSN
    -1.32
    UTC
    -1.26
    GROUND
    -1.25
     Citiz
    -1.20
    Official
    -1.19
    Grab
    -1.19
    Emb
    -1.19
    POSITIVE LOGITS
     apiece
    1.44
     respectively
    1.42
    henko
    1.39
    itton
    1.29
    gio
    1.28
    iHUD
    1.27
    etheless
    1.25
    uana
    1.25
    uple
    1.24
    escent
    1.23
    Activations Density 0.010%

    No Known Activations