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. 7-ATT-KK
    6. 9371
    Prev
    Next
    INDEX
    Explanations

    the word "go."

    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
    0:0.07
    1:0.09
    2:0.07
    3:0.08
    4:0.09
    5:0.08
    6:0.06
    7:0.08
    8:0.08
    9:0.08
    10:0.09
    11:0.07
    Negative Logits
    itely
    -2.35
    ivities
    -2.17
    ependent
    -2.10
    igue
    -2.08
    iaries
    -2.02
    iary
    -2.02
    ilda
    -1.94
    icol
    -1.89
    ipers
    -1.88
    wald
    -1.87
    POSITIVE LOGITS
     understatement
    2.35
    earch
    2.23
    ️
    1.89
     quir
    1.86
     mur
    1.83
     refining
    1.82
     zo
    1.81
     seismic
    1.80
     seism
    1.79
     compound
    1.78
    Activations Density 0.000%

    No Known Activations