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. 3-ATT-KK
    6. 8446
    Prev
    Next
    INDEX
    Explanations

    expressions of emotion and sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.07
    2:0.11
    3:0.02
    4:0.01
    5:0.02
    6:0.09
    7:0.17
    8:0.20
    9:0.15
    10:0.04
    11:0.06
    Negative Logits
     Corvette
    -1.15
     skate
    -1.12
    SHIP
    -1.10
     Gaul
    -1.09
     Grizzlies
    -1.07
     belonged
    -1.07
    �
    -1.06
     Cascade
    -1.05
     Sierra
    -1.05
     tariffs
    -1.03
    POSITIVE LOGITS
    avering
    1.41
    uti
    1.22
    inx
    1.17
    oing
    1.16
    ople
    1.14
    uding
    1.12
    arty
    1.09
    uble
    1.08
     wondering
    1.08
    tin
    1.08
    Activations Density 0.046%

    No Known Activations