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. 6386
    Prev
    Next
    INDEX
    Explanations

    phrases related to keeping things in a specific state or condition

    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
    1:0.07
    2:0.07
    3:0.03
    4:0.08
    5:0.08
    6:0.12
    7:0.05
    8:0.03
    9:0.03
    10:0.04
    11:0.24
    Negative Logits
    uncle
    -1.31
    Motor
    -1.21
    otor
    -1.19
    thus
    -1.16
    alph
    -1.15
    reve
    -1.12
    probably
    -1.11
    anch
    -1.10
    late
    -1.09
    ompl
    -1.09
    POSITIVE LOGITS
     Catalonia
    1.21
     Franch
    1.13
    vier
    1.13
    displayText
    1.11
     refunds
    1.10
     Aadhaar
    1.09
     Mondays
    1.08
     arbitration
    1.07
    tics
    1.05
     maintenance
    1.02
    Activations Density 0.043%

    No Known Activations