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. 7646
    Prev
    Next
    INDEX
    Explanations

    elements indicating mourning or sadness

    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
    0:0.04
    1:0.10
    2:0.02
    3:0.06
    4:0.03
    5:0.05
    6:0.20
    7:0.07
    8:0.01
    9:0.25
    10:0.04
    11:0.09
    Negative Logits
     tyr
    -3.25
    onder
    -3.05
     domain
    -2.97
    domain
    -2.88
     bom
    -2.84
     voic
    -2.81
    sol
    -2.80
    662
    -2.78
     rye
    -2.74
     licensee
    -2.73
    POSITIVE LOGITS
     Photos
    5.48
    Photos
    4.80
    actionDate
    3.92
    Ã
    3.62
    allery
    3.48
     Gallery
    3.45
     Hamm
    3.41
    assetsadobe
    3.34
     Carr
    3.33
     Hide
    3.22
    Activations Density 0.001%

    No Known Activations