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. 5-ATT-KK
    6. 7049
    Prev
    Next
    INDEX
    Explanations

    words associated with environmental impacts and climate-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.06
    3:0.05
    4:0.07
    5:0.03
    6:0.51
    7:0.03
    8:0.04
    9:0.04
    10:0.04
    11:0.04
    Negative Logits
    akia
    -1.19
    stadt
    -1.04
     universally
    -1.03
     nailed
    -1.02
    interstitial
    -1.02
     Via
    -1.02
     Sloan
    -1.00
    Publisher
    -0.98
    �
    -0.97
     Dev
    -0.96
    POSITIVE LOGITS
    pared
    1.48
    mble
    1.31
    quartered
    1.29
    ��
    1.28
    anol
    1.26
    alted
    1.22
    llor
    1.21
    riors
    1.20
    oeuv
    1.20
    MQ
    1.18
    Activations Density 0.325%

    No Known Activations