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. 6238
    Prev
    Next
    INDEX
    Explanations

    artists and art-related terms

    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
    1:0.05
    2:0.05
    3:0.02
    4:0.06
    5:0.18
    6:0.15
    7:0.05
    8:0.02
    9:0.02
    10:0.03
    11:0.20
    Negative Logits
     referral
    -1.10
    widget
    -1.07
     savings
    -1.07
     IPM
    -1.07
    istries
    -1.04
     Emails
    -1.02
    ounty
    -1.02
    GMT
    -1.02
     Featured
    -1.01
    arettes
    -1.00
    POSITIVE LOGITS
    pei
    1.13
    atism
    1.07
    Queen
    1.06
     Pepe
    1.05
    FactoryReloaded
    1.05
    Arch
    1.05
    orial
    1.04
    ITAL
    1.04
    Angelo
    1.03
    maid
    0.99
    Activations Density 0.026%

    No Known Activations