Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22314
    Prev
    Next
    INDEX
    Explanations

    instructions or prompts to take specific actions, typically involving clicks on buttons or links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.03
    2:0.07
    3:0.09
    4:0.03
    5:0.06
    6:0.05
    7:0.05
    8:0.25
    9:0.12
    10:0.07
    11:0.03
    Negative Logits
    istance
    -1.37
    pires
    -1.37
    ensable
    -1.37
    spection
    -1.32
    angering
    -1.31
    ctors
    -1.21
    ynthesis
    -1.21
    htaking
    -1.20
    aths
    -1.18
    nikov
    -1.16
    POSITIVE LOGITS
     button
    1.57
     tab
    1.28
    Brow
    1.27
    NRS
    1.26
     buttons
    1.22
    UI
    1.16
    MSN
    1.16
    rex
    1.14
     Eag
    1.14
     slider
    1.12
    Activations Density 0.034%

    No Known Activations