© 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. 2-ATT-KK
    6. 21410
    Prev
    Next
    INDEX
    Explanations

    references to the New York Times and its promotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of "The New York Times" and related promotional content

    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
    0:0.09
    1:0.06
    2:0.06
    3:0.08
    4:0.05
    5:0.08
    6:0.12
    7:0.07
    8:0.08
    9:0.10
    10:0.13
    11:0.04
    Negative Logits
    raltar
    -1.58
    awan
    -1.33
    ono
    -1.30
    icably
    -1.27
    ovember
    -1.26
     FAC
    -1.25
    kan
    -1.23
     Xavier
    -1.22
    rawled
    -1.19
    theless
    -1.18
    POSITIVE LOGITS
    )."
    1.96
    ]."
    1.91
    .'"
    1.75
    ."[
    1.64
    .")
    1.56
    '."
    1.52
     Gutenberg
    1.52
    %).
    1.46
    ").
    1.45
     Triumph
    1.41
    Activations Density 0.005%

    No Known Activations