© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 35228
    Prev
    Next
    INDEX
    Explanations

    negative language or sentiments related to authority and governance

    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
    0:0.01
    1:0.02
    2:0.15
    3:0.06
    4:0.05
    5:0.03
    6:0.31
    7:0.04
    8:0.03
    9:0.02
    10:0.16
    11:0.07
    Negative Logits
     perman
    -1.57
     unpredict
    -1.56
     rolls
    -1.50
    ashtra
    -1.43
     delinqu
    -1.42
    Ko
    -1.40
     whim
    -1.39
     Sweep
    -1.38
     malfunction
    -1.37
    iners
    -1.36
    POSITIVE LOGITS
    escription
    1.67
    enhagen
    1.66
     myster
    1.59
    ascript
    1.56
    ciating
    1.55
    director
    1.55
     franc
    1.55
    hesive
    1.54
    reau
    1.50
    rane
    1.45
    Activations Density 0.005%

    No Known Activations