© 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. 22002
    Prev
    Next
    INDEX
    Explanations

    references to null values in programming contexts

    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
    0:0.10
    1:0.03
    2:0.19
    3:0.09
    4:0.09
    5:0.06
    6:0.04
    7:0.03
    8:0.07
    9:0.15
    10:0.06
    11:0.03
    Negative Logits
    accompan
    -1.34
    kefeller
    -1.27
    ortment
    -1.27
    aldi
    -1.25
    soDeliveryDate
    -1.25
     Franç
    -1.23
    oulos
    -1.20
     mosqu
    -1.18
     Tiff
    -1.17
    ebus
    -1.15
    POSITIVE LOGITS
     nor
    1.11
     Void
    1.09
     oxide
    1.09
     void
    1.07
     Booker
    1.02
    liga
    1.01
    ��
    1.01
    oxide
    1.00
    gaard
    1.00
    ック
    0.99
    Activations Density 0.005%

    No Known Activations