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. 5-ATT-KK
    6. 19393
    Prev
    Next
    INDEX
    Explanations

    references to titles, ranks, or designations associated with nobility or aristocracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.04
    3:0.04
    4:0.04
    5:0.02
    6:0.31
    7:0.22
    8:0.03
    9:0.05
    10:0.13
    11:0.04
    Negative Logits
    nown
    -1.74
    yout
    -1.64
    tools
    -1.61
    atform
    -1.60
    parser
    -1.60
    earchers
    -1.58
    igslist
    -1.52
     scanners
    -1.49
     timet
    -1.46
    oaded
    -1.46
    POSITIVE LOGITS
     Duchess
    1.77
     Leaves
    1.60
     Monaco
    1.56
     Columbia
    1.51
     Neptune
    1.49
     Sierra
    1.48
     Witch
    1.47
     Wellington
    1.47
     Celebration
    1.47
     Florence
    1.46
    Activations Density 0.002%

    No Known Activations