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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 21395
    Prev
    Next
    INDEX
    Explanations

    phrases signaling instructions or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.03
    2:0.05
    3:0.06
    4:0.02
    5:0.05
    6:0.11
    7:0.15
    8:0.05
    9:0.05
    10:0.20
    11:0.09
    Negative Logits
    ••
    -0.95
    ''.
    -0.89
    .,"
    -0.89
    ".
    -0.86
    enegger
    -0.84
    .''
    -0.79
    ',"
    -0.78
     urgently
    -0.78
     grate
    -0.77
    �
    -0.77
    POSITIVE LOGITS
    panic
    0.86
    successful
    0.85
    illusion
    0.83
    seek
    0.82
    merce
    0.76
     Announce
    0.75
     CentOS
    0.73
    sych
    0.72
    Temp
    0.71
    DragonMagazine
    0.71
    Activations Density 0.069%

    No Known Activations