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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 42902
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal and political nuances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    2:0.14
    3:0.06
    4:0.12
    5:0.02
    6:0.02
    7:0.34
    8:0.07
    9:0.04
    10:0.04
    11:0.07
    Negative Logits
     Uriel
    -1.51
    iquette
    -1.49
     Drain
    -1.42
     Shu
    -1.40
     Swordsman
    -1.39
    msg
    -1.39
     Witch
    -1.37
     Bulk
    -1.36
     Refresh
    -1.34
     Tah
    -1.34
    POSITIVE LOGITS
    exclusive
    1.66
    ingen
    1.55
    teness
    1.49
    orthy
    1.43
     exclus
    1.43
     advantageous
    1.34
     nesting
    1.32
    Laun
    1.32
    enza
    1.30
     liabilities
    1.29
    Activations Density 0.021%

    No Known Activations