© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 46375
    Prev
    Next
    INDEX
    Explanations

    cooking-related phrases that highlight ease and comfort in recipes

    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
    2:0.04
    3:0.08
    4:0.04
    5:0.04
    6:0.03
    7:0.04
    8:0.04
    9:0.09
    10:0.37
    11:0.16
    Negative Logits
     patrols
    -1.41
     terminals
    -1.39
     lobbying
    -1.28
     monitors
    -1.27
     signalling
    -1.27
    adal
    -1.27
     signals
    -1.26
     exits
    -1.26
    hern
    -1.22
     resumes
    -1.21
    POSITIVE LOGITS
     ABV
    1.64
     recipe
    1.52
     recipes
    1.44
     Recipes
    1.43
    senal
    1.43
     compositions
    1.41
     cooker
    1.36
     recip
    1.34
     Paleo
    1.30
     ingred
    1.30
    Activations Density 0.221%

    No Known Activations