© 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. 28491
    Prev
    Next
    INDEX
    Explanations

    conditional statements related to hypothetical situations and outcomes

    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
    0:0.02
    1:0.01
    2:0.28
    3:0.18
    4:0.05
    5:0.03
    6:0.04
    7:0.03
    8:0.09
    9:0.06
    10:0.09
    11:0.06
    Negative Logits
    anmar
    -1.70
    pai
    -1.65
    kefeller
    -1.64
    veyard
    -1.62
    foundation
    -1.62
    mop
    -1.55
    jriwal
    -1.53
    ieve
    -1.52
    adra
    -1.52
    yright
    -1.50
    POSITIVE LOGITS
     shalt
    1.91
    魔
    1.54
     Offensive
    1.47
    held
    1.47
    edition
    1.45
     Norton
    1.43
    ilst
    1.41
    ケ
    1.38
    Shield
    1.36
     Correct
    1.35
    Activations Density 0.004%

    No Known Activations