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. 7634
    Prev
    Next
    INDEX
    Explanations

    terms related to health conditions and their implications

    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
    0:0.04
    1:0.05
    2:0.07
    3:0.04
    4:0.03
    5:0.04
    6:0.11
    7:0.28
    8:0.10
    9:0.03
    10:0.08
    11:0.07
    Negative Logits
    addons
    -1.26
    iple
    -1.25
    eph
    -1.21
    erie
    -1.16
    rand
    -1.16
    kr
    -1.15
    eeds
    -1.14
    action
    -1.11
    ohl
    -1.11
    them
    -1.10
    POSITIVE LOGITS
     Introduced
    1.39
    SPONSORED
    1.38
    ña
    1.36
     presided
    1.25
     Became
    1.20
    ilaterally
    1.18
     enshr
    1.17
     Vaj
    1.14
     Jinping
    1.14
    gemony
    1.13
    Activations Density 0.009%

    No Known Activations