© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21769
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to individuals or brands in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.03
    2:0.28
    3:0.07
    4:0.18
    5:0.06
    6:0.03
    7:0.02
    8:0.03
    9:0.06
    10:0.06
    11:0.03
    Negative Logits
     eleph
    -1.32
     clam
    -1.24
     squirrel
    -1.24
     fallacy
    -1.19
     ascend
    -1.16
    icans
    -1.16
     ebook
    -1.16
    steen
    -1.14
    -->
    -1.14
     spons
    -1.13
    POSITIVE LOGITS
    oslav
    1.70
    anski
    1.56
    士
    1.30
    udo
    1.30
    inis
    1.30
    uint
    1.29
    oker
    1.28
    gaard
    1.25
    uder
    1.25
    龍喚士
    1.22
    Activations Density 0.001%

    No Known Activations