© 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. 9-ATT-KK
    6. 18544
    Prev
    Next
    INDEX
    Explanations

    instances of rarity or uniqueness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.03
    2:0.07
    3:0.14
    4:0.02
    5:0.05
    6:0.03
    7:0.06
    8:0.03
    9:0.02
    10:0.43
    11:0.03
    Negative Logits
    )))
    -2.26
     angrily
    -2.24
    )].
    -2.17
    ))))
    -2.16
    )).
    -2.15
    tone
    -2.08
     escalate
    -2.06
    hani
    -1.99
     proport
    -1.98
     furiously
    -1.97
    POSITIVE LOGITS
     fortunate
    2.88
     exceptions
    2.84
     rare
    2.78
     lucky
    2.78
     exception
    2.69
     luck
    2.69
     occasion
    2.61
    Rare
    2.51
     exceptional
    2.51
     occasions
    2.48
    Activations Density 0.174%

    No Known Activations