© 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. 2-ATT-KK
    6. 22910
    Prev
    Next
    INDEX
    Explanations

    mentions of political or social controversy related to same-sex marriage or LGBT rights

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

    mentions of same-sex marriage and related controversies

    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
    0:0.05
    1:0.02
    2:0.24
    3:0.16
    4:0.11
    5:0.07
    6:0.01
    7:0.01
    8:0.07
    9:0.18
    10:0.03
    11:0.01
    Negative Logits
     extraord
    -1.23
     Peb
    -1.14
     Brig
    -1.08
     CAM
    -1.07
    esses
    -1.06
    kj
    -1.06
     Vu
    -1.06
    hern
    -1.06
     Kev
    -1.04
     disbanded
    -1.03
    POSITIVE LOGITS
    20439
    1.27
    WARE
    1.26
    セ
    1.22
    VALUE
    1.20
    �
    1.18
    ppings
    1.17
    assian
    1.16
    Availability
    1.16
    anon
    1.15
    hov
    1.14
    Activations Density 0.038%

    No Known Activations