© 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. 35194
    Prev
    Next
    INDEX
    Explanations

    conjunctions and mentions of organizations or entities involved in various 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
    0:0.03
    1:0.02
    2:0.06
    3:0.04
    4:0.07
    5:0.04
    6:0.44
    7:0.03
    8:0.05
    9:0.03
    10:0.07
    11:0.07
    Negative Logits
     Cloak
    -1.21
     Rhino
    -1.21
     Killer
    -1.19
     Whale
    -1.19
    ingo
    -1.18
     Papa
    -1.17
    stown
    -1.16
     Hog
    -1.15
    Safe
    -1.14
     Abbey
    -1.14
    POSITIVE LOGITS
    iliated
    1.54
    ilaterally
    1.46
    occup
    1.32
    iasco
    1.29
     relate
    1.29
    ocene
    1.26
     elect
    1.25
    elected
    1.25
    reetings
    1.24
     interacted
    1.24
    Activations Density 0.003%

    No Known Activations