Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 161
    Prev
    Next
    INDEX
    Explanations

    references to presidential power and military authority

    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
    0:0.11
    1:0.03
    2:0.24
    3:0.13
    4:0.04
    5:0.12
    6:0.03
    7:0.06
    8:0.07
    9:0.03
    10:0.06
    11:0.01
    Negative Logits
    ��
    -2.47
     Equality
    -2.16
     transpl
    -2.14
    married
    -2.06
     labou
    -2.06
     refunds
    -2.06
    ertation
    -2.04
     toilets
    -2.04
     gigs
    -1.99
     weddings
    -1.97
    POSITIVE LOGITS
     deterrence
    3.54
    escal
    3.44
     escalation
    3.42
     lethal
    3.42
    lethal
    3.40
     provocation
    3.35
     preempt
    3.25
    military
    3.25
     arming
    3.22
     missile
    3.22
    Activations Density 0.398%

    No Known Activations