© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 33880
    Prev
    Next
    INDEX
    Explanations

    negations or expressions of uncertainty

    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
    2:0.13
    3:0.36
    4:0.07
    5:0.03
    6:0.05
    7:0.06
    8:0.04
    9:0.04
    10:0.07
    11:0.06
    Negative Logits
    wx
    -1.80
    STEM
    -1.70
     respectively
    -1.65
    ocom
    -1.63
    osate
    -1.58
    knit
    -1.58
     progressively
    -1.51
    ankind
    -1.49
    EVA
    -1.47
     reconnect
    -1.46
    POSITIVE LOGITS
     pecul
    1.79
     irony
    1.78
     steroids
    1.76
     anyways
    1.70
     anymore
    1.65
     anyway
    1.64
     typo
    1.59
     haha
    1.55
     stuff
    1.54
    !).
    1.54
    Activations Density 0.004%

    No Known Activations