© 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. 10-ATT-KK
    11. 13545
    Prev
    Next
    INDEX
    Explanations

    instances of strong emotional expressions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.05
    2:0.10
    3:0.07
    4:0.07
    5:0.14
    6:0.06
    7:0.10
    8:0.04
    9:0.13
    10:0.04
    11:0.06
    Negative Logits
    owship
    -2.70
    arthed
    -2.51
     compass
    -2.44
    aredevil
    -2.40
    brates
    -2.34
    ochem
    -2.31
    scribe
    -2.30
     cease
    -2.27
    estinal
    -2.27
     CLS
    -2.27
    POSITIVE LOGITS
    �
    6.42
     �
    5.69
    ‎
    3.85
    �
    3.77
    �
    3.75
    ►
    3.70
    ■
    3.30
     �
    3.27
     hasht
    3.23
     �
    3.19
    Activations Density 0.071%

    No Known Activations