© 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. 42810
    Prev
    Next
    INDEX
    Explanations

    specific references to objects, items, or significant concepts within a narrative context

    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
    2:0.10
    3:0.10
    4:0.42
    5:0.02
    6:0.03
    7:0.06
    8:0.04
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
     populace
    -1.61
     listener
    -1.61
    conservancy
    -1.58
    iff
    -1.54
     industrialized
    -1.49
     guiActiveUnfocused
    -1.47
     alike
    -1.46
    uler
    -1.46
    ittee
    -1.44
    izens
    -1.43
    POSITIVE LOGITS
     Courage
    1.52
     handcuffs
    1.46
     Rampage
    1.42
     hol
    1.40
    BuyableInstoreAndOnline
    1.39
     ber
    1.39
     badges
    1.35
     Salvation
    1.32
    Title
    1.31
    uine
    1.31
    Activations Density 0.093%

    No Known Activations