© 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. 26328
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotional sentiments or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.10
    1:0.09
    2:0.08
    3:0.04
    4:0.02
    5:0.31
    6:0.12
    7:0.01
    8:0.05
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
     gre
    -1.76
     █
    -1.72
     sil
    -1.71
     dairy
    -1.65
    osaurus
    -1.62
    bery
    -1.62
    chwitz
    -1.61
     gel
    -1.59
     butter
    -1.58
     marsh
    -1.58
    POSITIVE LOGITS
    soDeliveryDate
    2.16
    Population
    2.15
    Ask
    2.09
    Requ
    2.07
    Operation
    2.03
    Recommended
    2.03
    continue
    2.02
    Same
    2.01
    Requires
    2.01
    Number
    2.00
    Activations Density 0.060%

    No Known Activations