© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21763
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate possession or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.01
    2:0.16
    3:0.03
    4:0.32
    5:0.06
    6:0.04
    7:0.02
    8:0.07
    9:0.14
    10:0.05
    11:0.02
    Negative Logits
    aryl
    -1.30
    talk
    -1.27
    Scar
    -1.22
    respective
    -1.20
    roy
    -1.17
    union
    -1.16
    nic
    -1.15
    hirt
    -1.10
    estine
    -1.10
    sic
    -1.10
    POSITIVE LOGITS
    illon
    1.58
    ensional
    1.49
    mberg
    1.46
    osaurs
    1.32
     Guilty
    1.32
     examples
    1.30
    ouf
    1.30
    bos
    1.29
    matical
    1.28
     Nero
    1.28
    Activations Density 0.017%

    No Known Activations