© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28176
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, primarily related to people

    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
    0:0.03
    1:0.01
    2:0.05
    3:0.05
    4:0.04
    5:0.04
    6:0.42
    7:0.07
    8:0.06
    9:0.07
    10:0.06
    11:0.05
    Negative Logits
    VICE
    -1.22
    TYPE
    -1.19
    lift
    -1.17
    pection
    -1.14
     lift
    -1.12
    PLIED
    -1.12
     iT
    -1.11
    gem
    -1.10
    guide
    -1.10
     exceptions
    -1.09
    POSITIVE LOGITS
    ioxide
    1.47
    ヘラ
    1.46
    ciating
    1.43
    apons
    1.38
    iewicz
    1.36
    opolis
    1.34
    ��
    1.33
    thia
    1.33
    emort
    1.32
    inous
    1.30
    Activations Density 0.003%

    No Known Activations