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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 19460
    Prev
    Next
    INDEX
    Explanations

    instances of aircraft being shot down

    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
    0:0.01
    1:0.01
    2:0.06
    3:0.06
    4:0.19
    5:0.03
    6:0.03
    7:0.33
    8:0.02
    9:0.04
    10:0.10
    11:0.06
    Negative Logits
    knit
    -1.74
    redo
    -1.68
    resh
    -1.65
    zel
    -1.60
    athered
    -1.59
    ]}
    -1.58
    ��
    -1.57
     scars
    -1.55
    olars
    -1.53
    rils
    -1.52
    POSITIVE LOGITS
     objections
    1.57
     unreasonable
    1.56
     objection
    1.54
     ambush
    1.47
     Viet
    1.45
    quickShipAvailable
    1.43
     assertions
    1.41
     presum
    1.38
     replies
    1.37
    SpaceEngineers
    1.36
    Activations Density 0.004%

    No Known Activations