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. 6433
    Prev
    Next
    INDEX
    Explanations

    words related to business growth and acquisitions

    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
    0:0.11
    1:0.05
    2:0.03
    3:0.01
    4:0.06
    5:0.12
    6:0.16
    7:0.08
    8:0.02
    9:0.02
    10:0.03
    11:0.28
    Negative Logits
    oplan
    -1.14
    ocol
    -1.12
    vision
    -1.08
    fab
    -1.06
    anship
    -1.05
    ocon
    -1.04
    opter
    -1.00
    abase
    -0.98
    osen
    -0.98
    plan
    -0.97
    POSITIVE LOGITS
    quickShipAvailable
    1.31
     Tradable
    1.21
     homophobia
    1.06
     GOODMAN
    1.05
     Discrimination
    1.04
     Poverty
    1.03
    ItemThumbnailImage
    1.00
     Hispanics
    0.99
    dated
    0.99
     Occupations
    0.99
    Activations Density 0.076%

    No Known Activations