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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 28394
    Prev
    Next
    INDEX
    Explanations

    content related to excessive lamentation or criticism

    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
    0:0.02
    1:0.01
    2:0.38
    3:0.14
    4:0.08
    5:0.02
    6:0.02
    7:0.05
    8:0.08
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
     Lithuan
    -1.51
     Andersen
    -1.34
    yssey
    -1.32
     unstoppable
    -1.31
     mash
    -1.30
     awaits
    -1.25
     shortly
    -1.24
     Baltic
    -1.22
     irresistible
    -1.22
     proverb
    -1.22
    POSITIVE LOGITS
     nor
    4.33
     anymore
    4.10
     whatsoever
    3.10
    nor
    2.76
     slightest
    2.39
     anything
    2.28
    soever
    2.27
     any
    2.22
     either
    2.18
     unless
    2.00
    Activations Density 2.110%

    No Known Activations