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. 3-ATT-KK
    6. 8555
    Prev
    Next
    INDEX
    Explanations

    past participles or actions indicating completed tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.04
    2:0.16
    3:0.02
    4:0.03
    5:0.09
    6:0.10
    7:0.06
    8:0.09
    9:0.06
    10:0.14
    11:0.07
    Negative Logits
    ZI
    -1.14
    leans
    -1.13
    shirts
    -1.03
    friends
    -1.02
     Situation
    -1.00
    lean
    -0.99
    hner
    -0.97
    olini
    -0.94
    tsky
    -0.94
    shoot
    -0.94
    POSITIVE LOGITS
    ependent
    1.21
    iquid
    1.17
    ioxide
    1.11
     charcoal
    0.98
     ubiqu
    0.97
     SCP
    0.95
     partName
    0.94
     accordance
    0.94
     separately
    0.94
     invis
    0.93
    Activations Density 0.155%

    No Known Activations