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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 13975
    Prev
    Next
    INDEX
    Explanations

    action verbs in the form of base verbs and contractions

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.10
    1:0.01
    2:0.29
    3:0.12
    4:0.05
    5:0.07
    6:0.08
    7:0.02
    8:0.04
    9:0.09
    10:0.06
    11:0.02
    Negative Logits
    Engineers
    -1.27
    achable
    -1.25
    egal
    -1.22
     tert
    -1.19
     elusive
    -1.16
     viability
    -1.15
    Els
    -1.15
    angular
    -1.13
    olid
    -1.12
    ull
    -1.12
    POSITIVE LOGITS
     yourselves
    1.73
     yourself
    1.67
    idences
    1.35
     Yourself
    1.29
    heit
    1.27
     Vault
    1.16
     Shoes
    1.15
     Profile
    1.15
     Trails
    1.13
     Wonderland
    1.12
    Activations Density 0.132%

    No Known Activations