© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 40048
    Prev
    Next
    INDEX
    Explanations

    noun forms and specific types of content related to political discussions

    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
    1:0.02
    2:0.04
    3:0.06
    4:0.05
    5:0.03
    6:0.50
    7:0.03
    8:0.04
    9:0.05
    10:0.05
    11:0.05
    Negative Logits
    WARD
    -1.46
     epit
    -1.26
     intersections
    -1.24
     stakes
    -1.22
     nails
    -1.21
     cones
    -1.20
     aggregation
    -1.20
     poles
    -1.20
    trak
    -1.19
     gears
    -1.19
    POSITIVE LOGITS
    ciating
    2.35
    ctory
    1.62
    ierre
    1.57
    �士
    1.48
    ciation
    1.48
    liction
    1.47
    opausal
    1.42
    gregation
    1.39
    �
    1.31
     guiName
    1.29
    Activations Density 0.011%

    No Known Activations