© 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. 10-ATT-KK
    6. 14465
    Prev
    Next
    INDEX
    Explanations

    identifiers or notable figures in the context of discussions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.13
    1:0.31
    2:0.03
    3:0.03
    4:0.03
    5:0.02
    6:0.05
    7:0.09
    8:0.03
    9:0.03
    10:0.14
    11:0.04
    Negative Logits
     Nemesis
    -3.06
     Icar
    -2.96
     magnets
    -2.86
    Ross
    -2.80
     Byrne
    -2.71
     magnet
    -2.64
    channelAvailability
    -2.60
     Carlson
    -2.56
    Allen
    -2.51
     Ragnar
    -2.49
    POSITIVE LOGITS
    ou
    5.59
     Nou
    5.44
     Chou
    4.97
     Kou
    4.73
     Sou
    4.68
     Mou
    4.56
     Gou
    4.52
    OU
    4.47
    ouk
    4.21
     Bou
    4.02
    Activations Density 0.005%

    No Known Activations