© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 16459
    Prev
    Next
    INDEX
    Explanations

    terms and adjectives that imply negativity or obsolescence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    2:0.04
    3:0.30
    4:0.13
    5:0.11
    6:0.03
    7:0.03
    8:0.06
    9:0.14
    10:0.02
    11:0.05
    Negative Logits
     wake
    -2.18
    ®,
    -2.06
     Yorkers
    -2.05
     Bulldogs
    -2.01
     Territories
    -1.98
     nightmares
    -1.92
     flames
    -1.91
     restraint
    -1.89
     Spartans
    -1.83
     Spit
    -1.81
    POSITIVE LOGITS
    ?)
    4.45
    -)
    4.11
    !)
    3.81
    ...)
    3.54
    ?)
    3.45
    )
    3.29
    /)
    3.25
    …)
    3.21
    ')
    3.17
    %)
    3.10
    Activations Density 0.034%

    No Known Activations