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. 8440
    Prev
    Next
    INDEX
    Explanations

    names or variations of the name "Mohammad."

    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
    1:0.05
    2:0.09
    3:0.22
    4:0.02
    5:0.02
    6:0.14
    7:0.07
    8:0.04
    9:0.09
    10:0.09
    11:0.09
    Negative Logits
    kefeller
    -1.29
    ���
    -1.25
     contingency
    -1.10
    Micro
    -1.05
    usterity
    -1.02
    PLA
    -1.01
     subp
    -0.99
    ��
    -0.99
     Pixar
    -0.97
    SpaceEngineers
    -0.94
    POSITIVE LOGITS
    schild
    1.47
    lah
    1.20
    nir
    1.15
    ahs
    1.07
    arine
    1.06
    orie
    1.02
    gh
    1.02
    gur
    1.01
    vard
    1.00
     gauge
    1.00
    Activations Density 0.003%

    No Known Activations