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. 7-ATT-KK
    6. 8952
    Prev
    Next
    INDEX
    Explanations

    references to real estate and property-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.31
    1:0.04
    2:0.00
    3:0.10
    4:0.11
    5:0.10
    6:0.04
    7:0.01
    8:0.05
    9:0.14
    10:0.01
    11:0.01
    Negative Logits
    resa
    -1.97
    ��
    -1.88
    akuya
    -1.80
    helle
    -1.78
    Wil
    -1.76
    ridor
    -1.75
    lez
    -1.74
    ricia
    -1.74
    pei
    -1.72
     Chung
    -1.70
    POSITIVE LOGITS
     acron
    2.24
     extremes
    1.96
     pitfalls
    1.95
     politics
    1.92
     gimm
    1.84
     tricks
    1.83
    balls
    1.82
     bashing
    1.80
     scares
    1.80
     dives
    1.76
    Activations Density 0.001%

    No Known Activations