© 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. 44797
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases that connect ideas

    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
    1:0.02
    2:0.14
    3:0.09
    4:0.22
    5:0.02
    6:0.11
    7:0.11
    8:0.05
    9:0.03
    10:0.06
    11:0.08
    Negative Logits
    alsh
    -1.62
     guiActiveUn
    -1.39
     horrors
    -1.32
    ipation
    -1.32
    anco
    -1.32
    ulsion
    -1.31
     Massacre
    -1.28
    lag
    -1.27
    onew
    -1.26
    thora
    -1.25
    POSITIVE LOGITS
    iqueness
    1.45
    isSpecialOrderable
    1.43
     alike
    1.43
     everywhere
    1.40
    always
    1.40
     regardless
    1.38
    soType
    1.38
    especially
    1.38
     hence
    1.32
    because
    1.29
    Activations Density 0.017%

    No Known Activations