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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43339
    Prev
    Next
    INDEX
    Explanations

    phrases that express commands or requests to stop, particularly in a confrontational context

    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
    0:0.01
    1:0.02
    2:0.06
    3:0.06
    4:0.20
    5:0.05
    6:0.09
    7:0.29
    8:0.04
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
    覚醒
    -2.15
    enegger
    -1.59
    QL
    -1.57
    merce
    -1.51
     Parables
    -1.42
    ModLoader
    -1.41
    cair
    -1.40
    cham
    -1.38
    ixel
    -1.38
    ��
    -1.38
    POSITIVE LOGITS
     leash
    1.89
     lid
    1.78
     doors
    1.77
     door
    1.75
     reins
    1.71
     drawer
    1.69
     brakes
    1.66
     accountable
    1.65
     Doors
    1.56
    eye
    1.54
    Activations Density 0.002%

    No Known Activations