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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7629
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing quantities or measurements

    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
    1:0.03
    2:0.07
    3:0.24
    4:0.02
    5:0.04
    6:0.07
    7:0.14
    8:0.04
    9:0.05
    10:0.16
    11:0.07
    Negative Logits
    shows
    -1.01
    sche
    -0.95
    rities
    -0.93
    tics
    -0.92
    fell
    -0.92
     academia
    -0.90
     Brune
    -0.90
     Fall
    -0.89
    429
    -0.89
    media
    -0.89
    POSITIVE LOGITS
    poons
    1.07
    elsius
    1.02
    ikuman
    1.01
    emis
    1.00
    assium
    0.98
    emouth
    0.97
    aditional
    0.97
     tradem
    0.95
    poon
    0.94
    Nitrome
    0.93
    Activations Density 0.049%

    No Known Activations