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. 7-ATT-KK
    6. 18943
    Prev
    Next
    INDEX
    Explanations

    references to specific names and terms related to a notable spacecraft or its missions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    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
    1:0.08
    2:0.20
    3:0.03
    4:0.02
    5:0.03
    6:0.03
    7:0.01
    8:0.02
    9:0.03
    10:0.42
    11:0.03
    Negative Logits
     Perse
    -2.40
     Rider
    -2.28
     Archdemon
    -2.25
     Horses
    -2.21
    729
    -2.18
     630
    -2.17
     Cassandra
    -2.13
     Jenna
    -2.11
     Carnage
    -2.08
     Gallagher
    -2.07
    POSITIVE LOGITS
    ut
    4.70
    UT
    4.43
    uts
    3.98
    uti
    3.79
    utt
    3.72
    utan
    3.48
    uto
    3.42
    uta
    3.33
    utor
    2.99
    UTE
    2.99
    Activations Density 0.003%

    No Known Activations