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. 10010
    Prev
    Next
    INDEX
    Explanations

    references to authorship and collaborations in creative or academic works

    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
    0:0.05
    1:0.03
    2:0.07
    3:0.12
    4:0.03
    5:0.03
    6:0.10
    7:0.07
    8:0.04
    9:0.03
    10:0.07
    11:0.32
    Negative Logits
    efficiency
    -1.20
    pron
    -1.15
     impression
    -1.08
     grains
    -1.06
     grav
    -1.06
     Feast
    -1.05
     msec
    -1.04
     impulse
    -1.01
     ItemLevel
    -0.99
     desired
    -0.98
    POSITIVE LOGITS
    ledged
    1.49
    nesday
    1.32
     collaborating
    1.28
    backer
    1.26
     partners
    1.25
     lia
    1.24
    isted
    1.23
    agonists
    1.23
    atinum
    1.22
     collaborations
    1.20
    Activations Density 0.028%

    No Known Activations