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. 1-ATT-KK
    6. 6453
    Prev
    Next
    INDEX
    Explanations

    information about events or situations happening since a specific year

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.08
    2:0.06
    3:0.03
    4:0.06
    5:0.12
    6:0.14
    7:0.05
    8:0.02
    9:0.03
    10:0.05
    11:0.20
    Negative Logits
    anooga
    -1.59
    merce
    -1.54
    uckland
    -1.45
    rights
    -1.44
    holes
    -1.44
    abus
    -1.43
    Companies
    -1.43
    amen
    -1.43
    MSN
    -1.42
    xual
    -1.42
    POSITIVE LOGITS
     Lethal
    1.37
     LW
    1.35
     drip
    1.31
     Deadly
    1.28
     Craw
    1.26
     AoE
    1.23
     DT
    1.23
     KH
    1.21
     fade
    1.20
     Cavern
    1.20
    Activations Density 0.041%

    No Known Activations