© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 45120
    Prev
    Next
    INDEX
    Explanations

    references to political rallies and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.05
    3:0.07
    4:0.07
    5:0.02
    6:0.02
    7:0.16
    8:0.03
    9:0.04
    10:0.32
    11:0.14
    Negative Logits
    krit
    -1.49
     mould
    -1.41
    gradation
    -1.37
     gene
    -1.33
     millennia
    -1.30
     unchecked
    -1.30
     genomes
    -1.28
    reated
    -1.28
    ��極
    -1.28
     nurt
    -1.28
    POSITIVE LOGITS
     rall
    1.72
    aturdays
    1.66
     rally
    1.41
    izza
    1.40
     rallies
    1.32
    okin
    1.31
    romptu
    1.31
    Interstitial
    1.30
     Daytona
    1.29
    Mot
    1.26
    Activations Density 0.019%

    No Known Activations