© 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. 22748
    Prev
    Next
    INDEX
    Explanations

    phrases related to news articles about political events and societal issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words indicating ongoing or completed actions over time

    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
    0:0.08
    1:0.01
    2:0.21
    3:0.03
    4:0.05
    5:0.07
    6:0.02
    7:0.08
    8:0.10
    9:0.03
    10:0.17
    11:0.08
    Negative Logits
    MG
    -0.90
    VICE
    -0.89
    early
    -0.78
    vice
    -0.77
    ゴン
    -0.76
    Brazil
    -0.76
     Guys
    -0.75
    SHIP
    -0.74
    assembly
    -0.74
     Industries
    -0.74
    POSITIVE LOGITS
    ilial
    0.99
    phas
    0.97
    ufficient
    0.95
    avering
    0.93
     sufficient
    0.91
    kefeller
    0.90
    been
    0.85
    iless
    0.85
    itud
    0.84
     occasion
    0.84
    Activations Density 0.538%

    No Known Activations