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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9183
    Prev
    Next
    INDEX
    Explanations

    references to behind-the-scenes activities or contexts

    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
    0:0.10
    1:0.08
    2:0.01
    3:0.08
    4:0.17
    5:0.06
    6:0.04
    7:0.03
    8:0.29
    9:0.05
    10:0.01
    11:0.02
    Negative Logits
    romy
    -2.66
    olon
    -2.55
    elta
    -2.50
    llor
    -2.43
    prus
    -2.23
    irlf
    -2.18
    emale
    -2.17
    rique
    -2.12
    uron
    -2.11
    aido
    -2.09
    POSITIVE LOGITS
     editorial
    2.12
     pockets
    2.12
     signage
    1.99
     editing
    1.96
     publicity
    1.96
     voic
    1.94
     whispering
    1.92
     commentary
    1.91
     VIDE
    1.91
     lobbying
    1.88
    Activations Density 0.001%

    No Known Activations