© 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. 3193
    Prev
    Next
    INDEX
    Explanations

    references to prominent individuals and accounts on social media

    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
    0:0.10
    1:0.24
    2:0.06
    3:0.06
    4:0.04
    5:0.15
    6:0.02
    7:0.04
    8:0.09
    9:0.06
    10:0.03
    11:0.05
    Negative Logits
     captcha
    -1.84
    pie
    -1.79
    idas
    -1.66
    NOR
    -1.57
    ══
    -1.55
    =/
    -1.52
    =$
    -1.51
    Bound
    -1.47
    match
    -1.44
    trip
    -1.44
    POSITIVE LOGITS
     Lub
    1.58
    neum
    1.54
     conclud
    1.52
    tml
    1.50
     Huss
    1.50
     Rear
    1.47
     testified
    1.47
     guiName
    1.46
     counsel
    1.46
    grave
    1.42
    Activations Density 0.002%

    No Known Activations