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. 18778
    Prev
    Next
    INDEX
    Explanations

    elements related to mourning and grief in the context of a sports tragedy

    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
    0:0.08
    1:0.03
    2:0.12
    3:0.10
    4:0.17
    5:0.09
    6:0.03
    7:0.06
    8:0.10
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
     ‎
    -2.99
     DRAG
    -2.78
     OW
    -2.74
    KC
    -2.73
    Export
    -2.73
     bye
    -2.54
    MG
    -2.54
    �
    -2.47
    haw
    -2.46
    ynt
    -2.43
    POSITIVE LOGITS
     gathers
    2.92
     reacts
    2.58
     crowds
    2.53
     believers
    2.41
     partisans
    2.40
     detects
    2.37
     attends
    2.37
     clustered
    2.35
     casts
    2.31
     participates
    2.26
    Activations Density 0.001%

    No Known Activations