© 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. 21740
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement or positivity towards specific subjects

    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
    0:0.11
    1:0.02
    2:0.14
    3:0.08
    4:0.04
    5:0.07
    6:0.06
    7:0.07
    8:0.19
    9:0.07
    10:0.06
    11:0.03
    Negative Logits
    rupal
    -3.25
    iasis
    -3.00
     PvP
    -2.80
     raids
    -2.80
     CoC
    -2.75
    reth
    -2.75
     Orthodox
    -2.69
    Gaza
    -2.64
     raided
    -2.63
     aggro
    -2.62
    POSITIVE LOGITS
     DeL
    6.99
     Truman
    3.57
     Einstein
    3.46
     Interstellar
    3.42
     transporter
    3.31
     relativity
    3.12
     Decker
    3.03
    atomic
    2.98
     Akira
    2.94
     Von
    2.90
    Activations Density 0.000%

    No Known Activations