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. 9379
    Prev
    Next
    INDEX
    Explanations

    specific actions and events related to movement and travel

    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
    0:0.03
    1:0.36
    2:0.02
    3:0.07
    4:0.01
    5:0.09
    6:0.13
    7:0.06
    8:0.06
    9:0.06
    10:0.03
    11:0.02
    Negative Logits
     antitrust
    -2.25
    metics
    -2.21
     royalties
    -2.18
     scandals
    -2.10
     scandal
    -2.06
     committees
    -2.06
     lobbyists
    -2.03
     patents
    -1.98
     moderators
    -1.97
     appointing
    -1.96
    POSITIVE LOGITS
     trek
    3.90
     travers
    3.63
     traverse
    3.48
     trave
    3.44
     travels
    3.34
     journey
    3.34
     disembark
    3.32
    travel
    3.26
     travelling
    3.26
     hitch
    3.22
    Activations Density 0.932%

    No Known Activations