© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22009
    Prev
    Next
    INDEX
    Explanations

    structured data and programming concepts related to object declaration and database interactions

    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
    1:0.08
    2:0.06
    3:0.08
    4:0.03
    5:0.07
    6:0.10
    7:0.08
    8:0.06
    9:0.10
    10:0.13
    11:0.07
    Negative Logits
    theless
    -1.67
    yss
    -1.57
    aeda
    -1.46
    田
    -1.43
    ECA
    -1.41
    etheless
    -1.41
    PLA
    -1.40
    arak
    -1.38
    accompan
    -1.33
    outhern
    -1.33
    POSITIVE LOGITS
     namespace
    1.39
     timestamp
    1.37
     Dictionary
    1.36
    Database
    1.34
     integer
    1.31
     lookup
    1.30
     User
    1.30
     decimal
    1.27
     Query
    1.27
     args
    1.26
    Activations Density 0.087%

    No Known Activations