© 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. 18992
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparative relationships and opposing viewpoints

    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
    0:0.06
    1:0.02
    2:0.09
    3:0.05
    4:0.32
    5:0.03
    6:0.03
    7:0.07
    8:0.12
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
     paused
    -1.69
    gently
    -1.50
    ayne
    -1.42
     Remastered
    -1.40
     thanked
    -1.39
     awake
    -1.38
    foreseen
    -1.38
     congratulated
    -1.35
     awoke
    -1.35
    ���
    -1.33
    POSITIVE LOGITS
     ones
    1.84
     others
    1.62
    Others
    1.53
     weeds
    1.52
    aurus
    1.42
    tis
    1.37
    esson
    1.36
     rivals
    1.34
     norms
    1.32
    NULL
    1.32
    Activations Density 0.019%

    No Known Activations