© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 2338
    Prev
    Next
    INDEX
    Explanations

    references to the Flint water crisis and its associated events and impacts on residents

    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
    0:0.02
    1:0.01
    2:0.05
    3:0.04
    4:0.05
    5:0.05
    6:0.04
    7:0.04
    8:0.04
    9:0.06
    10:0.42
    11:0.13
    Negative Logits
    lance
    -1.90
     Psal
    -1.69
     Socrates
    -1.63
     Orn
    -1.56
     notation
    -1.56
     sax
    -1.54
     motif
    -1.53
     gust
    -1.51
     harmonic
    -1.50
     Hegel
    -1.48
    POSITIVE LOGITS
     contaminated
    1.80
     harmed
    1.77
    CDC
    1.76
     medically
    1.70
     hepatitis
    1.63
     population
    1.61
     hemorrh
    1.59
     devastated
    1.56
     suffered
    1.55
     ruined
    1.55
    Activations Density 0.005%

    No Known Activations