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. 20691
    Prev
    Next
    INDEX
    Explanations

    events related to community gatherings or festivals

    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
    0:0.10
    1:0.03
    2:0.12
    3:0.07
    4:0.18
    5:0.09
    6:0.03
    7:0.18
    8:0.04
    9:0.03
    10:0.05
    11:0.03
    Negative Logits
    agate
    -2.62
    weak
    -2.42
    ��極
    -2.41
    addons
    -2.38
    redit
    -2.25
     tyrann
    -2.23
    ndra
    -2.21
    olean
    -2.15
    nexus
    -2.08
    enment
    -2.07
    POSITIVE LOGITS
    Tickets
    4.71
     Tickets
    4.12
    Thursday
    3.73
    Saturday
    3.69
    Sunday
    3.63
    Friday
    3.60
    Wednesday
    3.59
    Tuesday
    3.48
     Admission
    3.46
    Monday
    3.44
    Activations Density 0.782%

    No Known Activations