© 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. 19763
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditions and dependencies in logical or procedural contexts

    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
    0:0.13
    1:0.22
    2:0.05
    3:0.03
    4:0.03
    5:0.17
    6:0.05
    7:0.02
    8:0.10
    9:0.06
    10:0.04
    11:0.03
    Negative Logits
    zl
    -1.81
    HK
    -1.50
    abul
    -1.49
    unic
    -1.46
     Plum
    -1.45
    ogg
    -1.42
    agnar
    -1.42
    Rated
    -1.42
     Hes
    -1.38
    kk
    -1.36
    POSITIVE LOGITS
    )=(
    1.92
     preferably
    1.77
     proport
    1.56
    作
    1.56
    uary
    1.53
     mainly
    1.49
     replication
    1.46
     proxies
    1.42
     leveraging
    1.41
     exporting
    1.40
    Activations Density 0.003%

    No Known Activations