© 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. 2-ATT-KK
    11. 15263
    Prev
    Next
    INDEX
    Explanations

    mentions of the brand "Mercedes-Benz."

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    1:0.04
    2:0.20
    3:0.07
    4:0.12
    5:0.07
    6:0.04
    7:0.04
    8:0.06
    9:0.14
    10:0.08
    11:0.04
    Negative Logits
    :]
    -1.30
    lishes
    -1.27
    KEY
    -1.23
    literally
    -1.22
     Pipe
    -1.21
     Cree
    -1.16
    scribe
    -1.15
    mouth
    -1.13
    keyes
    -1.12
    hower
    -1.12
    POSITIVE LOGITS
    Benz
    1.33
     Boost
    1.28
    essel
    1.17
    vertisement
    1.10
    士
    1.08
     lapt
    1.06
     Tomorrow
    1.02
    htar
    1.02
     ticket
    1.01
     trainers
    1.00
    Activations Density 0.004%

    No Known Activations