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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 2882
    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 @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.06
    2:0.04
    3:0.07
    4:0.05
    5:0.06
    6:0.04
    7:0.11
    8:0.04
    9:0.03
    10:0.17
    11:0.22
    Negative Logits
     concess
    -2.34
    rocal
    -2.19
    raltar
    -2.15
    uty
    -2.12
    verages
    -2.11
    interstitial
    -2.11
    oided
    -2.08
     Nicarag
    -2.03
    lished
    -2.02
    osate
    -2.02
    POSITIVE LOGITS
    �
    6.34
     �
    5.81
    .—
    4.77
    ––
    4.62
    �
    4.61
    �
    4.59
    ­
    4.51
     �
    4.48
    †
    4.44
    �
    4.38
    Activations Density 0.316%

    No Known Activations