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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9996
    Prev
    Next
    INDEX
    Explanations

    terms related to climate change and its effects

    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
    0:0.04
    1:0.03
    2:0.08
    3:0.08
    4:0.02
    5:0.06
    6:0.13
    7:0.27
    8:0.06
    9:0.04
    10:0.08
    11:0.05
    Negative Logits
     Maz
    -1.22
    iture
    -1.19
     Ov
    -1.11
    FN
    -1.05
     detailing
    -1.02
     specialize
    -1.01
    ensical
    -1.00
     dishes
    -1.00
    :{
    -0.99
    onomy
    -0.99
    POSITIVE LOGITS
    ioxide
    1.57
    ��
    1.47
    acerb
    1.30
    ynthesis
    1.28
     stagn
    1.24
    ageddon
    1.23
     �
    1.21
     サーティワン
    1.19
    phase
    1.18
    gnu
    1.18
    Activations Density 0.021%

    No Known Activations