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. 9-ATT-KK
    6. 20629
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial contributions and support for journalism

    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
    0:0.17
    1:0.03
    2:0.11
    3:0.10
    4:0.02
    5:0.16
    6:0.07
    7:0.05
    8:0.13
    9:0.01
    10:0.09
    11:0.02
    Negative Logits
     BMW
    -2.59
     Kyoto
    -2.56
    ø
    -2.36
     Norway
    -2.30
    å
    -2.30
     Stockholm
    -2.28
    vard
    -2.25
     Volvo
    -2.23
     ther
    -2.18
     Seoul
    -2.16
    POSITIVE LOGITS
    Dispatch
    2.98
    Writ
    2.65
    utenberg
    2.61
    Writer
    2.55
     Journalism
    2.52
     Rebels
    2.49
     circulation
    2.46
    Print
    2.45
    artifacts
    2.44
    Dash
    2.43
    Activations Density 0.007%

    No Known Activations