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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43505
    Prev
    Next
    INDEX
    Explanations

    instances of the word "writing" and variations of it

    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
    1:0.01
    2:0.08
    3:0.04
    4:0.15
    5:0.03
    6:0.08
    7:0.21
    8:0.04
    9:0.04
    10:0.05
    11:0.21
    Negative Logits
    Letter
    -1.83
     chapter
    -1.76
    letter
    -1.70
    inventoryQuantity
    -1.69
     nightmares
    -1.67
     Letter
    -1.66
     seriousness
    -1.63
    blog
    -1.62
     illustrations
    -1.62
     chapters
    -1.61
    POSITIVE LOGITS
    goers
    1.70
    ezvous
    1.56
    NetMessage
    1.56
    gear
    1.54
    legates
    1.53
     stationed
    1.52
     safely
    1.52
    robe
    1.52
     teleport
    1.51
     comply
    1.51
    Activations Density 0.000%

    No Known Activations