Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22626
    Prev
    Next
    INDEX
    Explanations

    references to the "Lord of the Rings" series

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to "The Lord of the Rings" and associated characters

    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
    0:0.07
    1:0.04
    2:0.20
    3:0.08
    4:0.11
    5:0.08
    6:0.02
    7:0.02
    8:0.05
    9:0.21
    10:0.05
    11:0.02
    Negative Logits
     offline
    -1.28
     complementary
    -1.26
    */(
    -1.25
     bout
    -1.21
    ories
    -1.17
    anwhile
    -1.17
     dots
    -1.16
     mats
    -1.14
    ometime
    -1.14
     sidelines
    -1.11
    POSITIVE LOGITS
     Glory
    1.56
    iHUD
    1.46
     Beasts
    1.29
     Wisdom
    1.28
     Honour
    1.28
    Crypt
    1.28
    chief
    1.25
    itus
    1.23
     Rath
    1.23
     Majesty
    1.22
    Activations Density 0.015%

    No Known Activations