Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14704
    Prev
    Next
    INDEX
    Explanations

    processes and methods related to blending or mixing ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.07
    2:0.07
    3:0.08
    4:0.13
    5:0.05
    6:0.06
    7:0.08
    8:0.05
    9:0.09
    10:0.07
    11:0.09
    Negative Logits
     Telecom
    -2.63
     fielded
    -2.44
    士
    -2.43
    senal
    -2.35
     headlined
    -2.35
     Ranked
    -2.24
     Telecommunications
    -2.23
    trak
    -2.21
     headquartered
    -2.20
     Kahn
    -2.18
    POSITIVE LOGITS
     rinse
    4.34
     moist
    3.99
     shampoo
    3.77
     spray
    3.71
     wet
    3.69
     moistur
    3.67
     drip
    3.64
     wash
    3.60
     drying
    3.55
     dry
    3.51
    Activations Density 0.162%

    No Known Activations