© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43394
    Prev
    Next
    INDEX
    Explanations

    requests for contact and communication information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.02
    2:0.09
    3:0.09
    4:0.20
    5:0.03
    6:0.06
    7:0.13
    8:0.04
    9:0.04
    10:0.09
    11:0.15
    Negative Logits
     immune
    -1.22
            
    -1.20
    rived
    -1.19
    ULTS
    -1.16
    unin
    -1.13
    terday
    -1.12
    luent
    -1.11
     unwittingly
    -1.10
     traditionally
    -1.10
    arnaev
    -1.09
    POSITIVE LOGITS
    abouts
    1.61
    Road
    1.34
     trave
    1.33
     coaches
    1.27
    BuyableInstoreAndOnline
    1.25
    Coach
    1.25
     sugg
    1.24
     gobl
    1.24
    License
    1.22
     murd
    1.22
    Activations Density 0.003%

    No Known Activations