© 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. 28284
    Prev
    Next
    INDEX
    Explanations

    phrases related to government and authority

    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
    0:0.04
    1:0.02
    2:0.05
    3:0.04
    4:0.07
    5:0.03
    6:0.20
    7:0.30
    8:0.03
    9:0.03
    10:0.07
    11:0.07
    Negative Logits
     flashbacks
    -1.85
    inventoryQuantity
    -1.73
     nostalg
    -1.66
     concess
    -1.59
    Tokens
    -1.47
    urat
    -1.46
     greedy
    -1.46
     friendly
    -1.43
     scenarios
    -1.42
    acci
    -1.39
    POSITIVE LOGITS
    stown
    1.53
    osite
    1.53
    anguages
    1.46
     Jaw
    1.44
    warts
    1.39
    inois
    1.34
     Graduate
    1.31
     Desk
    1.31
     tallest
    1.30
     Faculty
    1.29
    Activations Density 0.004%

    No Known Activations