© 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. 8966
    Prev
    Next
    INDEX
    Explanations

    references to emotional responses or reactions in discourse

    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
    0:0.21
    1:0.09
    2:0.07
    3:0.06
    4:0.03
    5:0.06
    6:0.01
    7:0.02
    8:0.22
    9:0.06
    10:0.05
    11:0.06
    Negative Logits
    eatures
    -2.01
     destro
    -1.79
     reluct
    -1.73
     describ
    -1.68
    cffff
    -1.63
     confir
    -1.58
     perpend
    -1.56
     spons
    -1.55
     livest
    -1.54
    oğ
    -1.51
    POSITIVE LOGITS
    Said
    1.98
     Tears
    1.81
    Trivia
    1.59
    -->
    1.58
    �
    1.55
    ]]
    1.53
    )=
    1.49
     Said
    1.46
    said
    1.40
    "'
    1.38
    Activations Density 0.008%

    No Known Activations