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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22006
    Prev
    Next
    INDEX
    Explanations

    terms related to radioactive materials and their uses in nuclear processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.05
    2:0.19
    3:0.07
    4:0.10
    5:0.09
    6:0.03
    7:0.04
    8:0.07
    9:0.18
    10:0.07
    11:0.02
    Negative Logits
    YOU
    -1.36
    ICO
    -1.35
    AME
    -1.35
    Nusra
    -1.33
    INST
    -1.32
    andals
    -1.32
    Kids
    -1.31
    ━
    -1.30
    ESPN
    -1.30
    nesday
    -1.29
    POSITIVE LOGITS
    ioxide
    1.90
     plutonium
    1.41
     oxide
    1.40
     cere
    1.40
     phosphorus
    1.38
     Substance
    1.37
    cius
    1.36
    ethy
    1.36
     phosphate
    1.35
     irrad
    1.34
    Activations Density 0.009%

    No Known Activations