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. 18788
    Prev
    Next
    INDEX
    Explanations

    references to political discussions and local government activities

    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
    0:0.07
    1:0.02
    2:0.09
    3:0.09
    4:0.03
    5:0.08
    6:0.03
    7:0.04
    8:0.42
    9:0.05
    10:0.03
    11:0.02
    Negative Logits
     Finnish
    -3.91
    ä
    -3.75
    NZ
    -3.72
     civilisation
    -3.71
     Finland
    -3.60
    Japan
    -3.59
    Japanese
    -3.52
     Brisbane
    -3.49
     analyse
    -3.44
     tyre
    -3.42
    POSITIVE LOGITS
     DC
    4.28
    DC
    4.09
     Dull
    3.91
     Maryland
    3.88
    Baltimore
    3.68
     Georgetown
    3.67
     Baltimore
    3.63
     District
    3.58
     Washington
    3.54
     Capitol
    3.52
    Activations Density 0.020%

    No Known Activations