Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 9089
    Prev
    Next
    INDEX
    Explanations

    lists of countries and their corresponding characteristics or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.02
    3:0.05
    4:0.03
    5:0.15
    6:0.08
    7:0.15
    8:0.07
    9:0.09
    10:0.03
    11:0.19
    Negative Logits
    BAT
    -2.30
    ertodd
    -2.26
    CRIP
    -2.20
    arsity
    -2.13
    BALL
    -2.04
    uscript
    -2.04
    ocious
    -2.01
    inventoryQuantity
    -2.00
     WATCHED
    -2.00
    bral
    -2.00
    POSITIVE LOGITS
     Netherlands
    4.07
     Norway
    3.65
     France
    3.64
     Denmark
    3.38
     Malta
    3.32
     Sweden
    3.31
     Iceland
    3.30
     Finland
    3.21
     Poland
    3.13
     Luxembourg
    3.13
    Activations Density 0.015%

    No Known Activations