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. 8304
    Prev
    Next
    INDEX
    Explanations

    positive emotional states and evaluations of experiences

    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
    0:0.01
    1:0.03
    2:0.18
    3:0.11
    4:0.01
    5:0.04
    6:0.04
    7:0.11
    8:0.08
    9:0.21
    10:0.06
    11:0.06
    Negative Logits
    ��
    -0.98
     remembrance
    -0.97
     commemor
    -0.97
    eming
    -0.96
    nm
    -0.95
     Notting
    -0.93
    Display
    -0.92
    lines
    -0.90
     dishes
    -0.89
    batch
    -0.88
    POSITIVE LOGITS
    ◼
    1.06
    ricanes
    1.06
    isson
    1.05
     deviations
    1.04
     Berg
    1.03
     srfAttach
    0.98
     deviation
    0.98
     tiss
    0.97
     Directorate
    0.96
     IPM
    0.96
    Activations Density 0.015%

    No Known Activations