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. 5-ATT-KK
    6. 44114
    Prev
    Next
    INDEX
    Explanations

    phrases indicating various states of being or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.02
    2:0.06
    3:0.05
    4:0.04
    5:0.04
    6:0.03
    7:0.25
    8:0.06
    9:0.06
    10:0.25
    11:0.05
    Negative Logits
     govern
    -2.04
     dictate
    -1.84
     dictated
    -1.79
     governs
    -1.77
     FTA
    -1.74
    Rules
    -1.71
     governed
    -1.65
     deficit
    -1.63
     payout
    -1.62
    controlled
    -1.62
    POSITIVE LOGITS
    akura
    1.85
    aganda
    1.70
    aphael
    1.69
     Ambrose
    1.67
     Hubble
    1.66
     unexpl
    1.64
    ilet
    1.62
    nsics
    1.59
    rium
    1.57
    agher
    1.57
    Activations Density 0.002%

    No Known Activations