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. 3-ATT-KK
    6. 8306
    Prev
    Next
    INDEX
    Explanations

    references to photography and photographic content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.07
    3:0.28
    4:0.01
    5:0.03
    6:0.10
    7:0.18
    8:0.05
    9:0.03
    10:0.09
    11:0.06
    Negative Logits
    FUL
    -1.06
    aughs
    -1.06
    full
    -1.06
     listens
    -1.03
     territories
    -1.03
    た
    -1.03
     innovate
    -1.01
     reliance
    -1.00
    ��
    -0.98
     communism
    -0.98
    POSITIVE LOGITS
     GCC
    1.10
     Malt
    1.10
     Photograph
    1.09
    aminer
    1.08
    ographer
    1.04
     Marble
    1.04
     Marina
    1.04
    ographers
    1.04
    ography
    1.03
    ogle
    1.02
    Activations Density 0.033%

    No Known Activations