© 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. 9-ATT-KK
    11. 13819
    Prev
    Next
    INDEX
    Explanations

    questions and interactions related to personal experiences or emotional support

    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
    0:0.15
    1:0.02
    2:0.37
    3:0.10
    4:0.03
    5:0.07
    6:0.02
    7:0.06
    8:0.03
    9:0.03
    10:0.04
    11:0.01
    Negative Logits
    ikhail
    -2.79
     cannibal
    -2.74
     amput
    -2.65
     docking
    -2.63
    kefeller
    -2.60
    illac
    -2.54
     smashed
    -2.43
     losses
    -2.42
    nants
    -2.41
     exported
    -2.37
    POSITIVE LOGITS
     answers
    6.37
     Answers
    6.08
     answ
    5.84
    Answer
    5.62
     Answer
    5.58
    answer
    5.57
     answering
    5.46
    swers
    5.40
     answer
    5.34
     answered
    5.27
    Activations Density 0.451%

    No Known Activations