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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 27578
    Prev
    Next
    INDEX
    Explanations

    concepts related to modern ideologies and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.35
    3:0.09
    4:0.07
    5:0.05
    6:0.06
    7:0.03
    8:0.04
    9:0.06
    10:0.09
    11:0.07
    Negative Logits
     sidx
    -1.89
     thereof
    -1.46
     thereto
    -1.40
     afore
    -1.34
    ヴァ
    -1.32
     laun
    -1.31
    liest
    -1.29
    assad
    -1.27
    zl
    -1.24
    elfth
    -1.22
    POSITIVE LOGITS
     abound
    2.03
     ⓘ
    1.58
    ¶
    1.49
    geries
    1.39
     meanwhile
    1.36
     sprang
    1.35
     indeed
    1.33
     Redux
    1.32
     rife
    1.32
     cropped
    1.32
    Activations Density 0.718%

    No Known Activations