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. 10225
    Prev
    Next
    INDEX
    Explanations

    prepositions that indicate locations or relationships

    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
    1:0.01
    2:0.09
    3:0.31
    4:0.02
    5:0.02
    6:0.06
    7:0.10
    8:0.06
    9:0.13
    10:0.05
    11:0.09
    Negative Logits
    ificial
    -1.21
    boa
    -1.11
    tackle
    -1.06
    piration
    -1.05
     Vas
    -1.04
    uming
    -1.04
     Mandela
    -1.03
     Hawai
    -1.03
    amiya
    -1.01
    azy
    -1.01
    POSITIVE LOGITS
    覚醒
    1.27
    erenn
    1.24
     Err
    1.12
     ENTER
    1.10
     nightly
    1.09
    illet
    1.08
     Reporter
    1.07
     Errors
    1.07
    @#&
    1.06
     Conduct
    1.06
    Activations Density 0.020%

    No Known Activations