© 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. 12399
    Prev
    Next
    INDEX
    Explanations

    statements and reports concerning actions and decisions

    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
    0:0.07
    1:0.02
    2:0.13
    3:0.15
    4:0.05
    5:0.27
    6:0.03
    7:0.08
    8:0.04
    9:0.03
    10:0.06
    11:0.02
    Negative Logits
    yip
    -2.66
     newspapers
    -2.16
    addafi
    -2.09
     tabl
    -2.03
     Thatcher
    -1.99
     tattoos
    -1.96
     tattoo
    -1.95
    Putin
    -1.89
    abal
    -1.88
     KGB
    -1.88
    POSITIVE LOGITS
    Statement
    2.10
     Continuing
    1.97
     NON
    1.93
     participating
    1.91
     Accordingly
    1.87
     tresp
    1.84
     Gravity
    1.84
     UPDATE
    1.84
     Participant
    1.84
     Contest
    1.82
    Activations Density 0.268%

    No Known Activations