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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 7681
    Prev
    Next
    INDEX
    Explanations

    terms related to pontifical authority and religious context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.04
    2:0.10
    3:0.23
    4:0.02
    5:0.02
    6:0.11
    7:0.11
    8:0.04
    9:0.09
    10:0.06
    11:0.11
    Negative Logits
    jriwal
    -1.35
    nesday
    -1.31
    eco
    -1.15
     ponds
    -1.12
     horizont
    -1.11
    orest
    -1.11
    owship
    -1.10
    rison
    -1.08
     predators
    -1.08
    monton
    -1.07
    POSITIVE LOGITS
     Tid
    1.33
    将
    1.26
     chap
    1.19
     XIV
    1.18
    Royal
    1.17
    �
    1.15
    �
    1.15
    STATE
    1.14
    �士
    1.13
     Blossom
    1.12
    Activations Density 0.002%

    No Known Activations