© 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. 21757
    Prev
    Next
    INDEX
    Explanations

    key terms related to media coverage and reports on significant societal issues

    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
    1:0.02
    2:0.08
    3:0.18
    4:0.02
    5:0.17
    6:0.02
    7:0.05
    8:0.03
    9:0.12
    10:0.12
    11:0.06
    Negative Logits
     Tone
    -1.70
     Tune
    -1.50
     Investor
    -1.47
    icism
    -1.34
     Religion
    -1.32
     Reader
    -1.29
     Bernstein
    -1.27
     Canary
    -1.25
     Romance
    -1.25
     Wolfe
    -1.25
    POSITIVE LOGITS
    覚醒
    1.62
     apiece
    1.41
    imore
    1.35
    riots
    1.32
    aways
    1.31
    votes
    1.31
    frames
    1.30
    secut
    1.27
    PsyNetMessage
    1.26
    tackle
    1.24
    Activations Density 0.396%

    No Known Activations