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. 9-ATT-KK
    6. 18735
    Prev
    Next
    INDEX
    Explanations

    constructs that involve government-related discussions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.06
    3:0.22
    4:0.02
    5:0.11
    6:0.03
    7:0.08
    8:0.02
    9:0.02
    10:0.28
    11:0.03
    Negative Logits
    .–
    -2.07
    "></
    -1.96
     Photograph
    -1.95
     Incarnation
    -1.93
     Repeat
    -1.88
     =>
    -1.87
     Finished
    -1.84
    ***
    -1.77
     Entered
    -1.76
    reath
    -1.76
    POSITIVE LOGITS
     rivalry
    2.24
     dues
    2.07
     lobbyists
    2.02
     antitrust
    1.94
     lawsuits
    1.93
     animosity
    1.91
     gearing
    1.90
    immune
    1.89
     monopol
    1.88
    lux
    1.88
    Activations Density 0.010%

    No Known Activations