© 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. 5-ATT-KK
    6. 35559
    Prev
    Next
    INDEX
    Explanations

    references to harmful chemicals and their effects

    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
    2:0.09
    3:0.07
    4:0.06
    5:0.08
    6:0.03
    7:0.03
    8:0.07
    9:0.10
    10:0.20
    11:0.18
    Negative Logits
    igue
    -1.00
    fortune
    -0.94
    aye
    -0.93
    nir
    -0.92
    uden
    -0.91
    arb
    -0.91
    stairs
    -0.87
    zig
    -0.87
     glim
    -0.85
    insula
    -0.84
    POSITIVE LOGITS
     Hobby
    1.03
    ItemImage
    0.95
     Manufacturer
    0.88
     Reprodu
    0.88
    VERTISEMENT
    0.87
     Roh
    0.83
     RF
    0.83
     therefore
    0.81
    Edited
    0.81
     Generation
    0.81
    Activations Density 0.461%

    No Known Activations