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. 3-ATT-KK
    6. 10177
    Prev
    Next
    INDEX
    Explanations

    words associated with temperature variations or extreme weather conditions

    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
    3:0.34
    4:0.02
    5:0.02
    6:0.09
    7:0.11
    8:0.03
    9:0.07
    10:0.06
    11:0.09
    Negative Logits
    emort
    -1.59
    ittal
    -1.39
    amera
    -1.17
    Privacy
    -1.13
    iles
    -1.11
    ACY
    -1.09
    utable
    -1.05
    last
    -1.04
    ruct
    -1.04
     Deaths
    -1.03
    POSITIVE LOGITS
    oglobin
    1.38
    ween
    1.24
     bothered
    1.23
     Reloaded
    1.23
     attracting
    1.15
    rish
    1.15
     HOT
    1.12
     adrenaline
    1.12
    Thumbnail
    1.11
     viz
    1.05
    Activations Density 0.013%

    No Known Activations