© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 23000
    Prev
    Next
    INDEX
    Explanations

    phrases related to research studies and investigation findings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of individuals and organizations in contexts related to political or institutional matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.02
    2:0.15
    3:0.08
    4:0.02
    5:0.07
    6:0.03
    7:0.07
    8:0.03
    9:0.21
    10:0.14
    11:0.07
    Negative Logits
     Italians
    -1.30
    PDATE
    -1.29
    iterranean
    -1.20
    TRY
    -1.07
    isSpecial
    -1.04
    ormonal
    -1.03
     asses
    -1.02
     Doomsday
    -1.02
     footing
    -1.01
     unbeliev
    -1.00
    POSITIVE LOGITS
     LLP
    1.42
     QC
    1.27
     PhD
    1.24
     MD
    1.24
    bra
    1.21
    jee
    1.14
    ophon
    1.12
    essen
    1.11
    ben
    1.09
    Buzz
    1.08
    Activations Density 0.637%

    No Known Activations