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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7801
    Prev
    Next
    INDEX
    Explanations

    phrases related to suppression or control of various aspects, including emotions and expressions

    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
    0:0.02
    1:0.03
    2:0.06
    3:0.12
    4:0.01
    5:0.04
    6:0.06
    7:0.11
    8:0.12
    9:0.18
    10:0.07
    11:0.13
    Negative Logits
     largeDownload
    -1.30
    urai
    -1.21
    sonian
    -1.17
    itz
    -1.15
     Zup
    -1.12
    inav
    -1.11
    liest
    -1.11
    psc
    -1.10
    hani
    -1.09
    yssey
    -1.08
    POSITIVE LOGITS
    alien
    1.29
     altogether
    1.20
     dissent
    1.18
    urities
    1.15
     extremism
    1.10
     whatsoever
    1.09
     democratically
    1.05
     falsely
    1.05
     stigma
    1.05
     terrorism
    1.04
    Activations Density 0.013%

    No Known Activations