© 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. 10-ATT-KK
    11. 14967
    Prev
    Next
    INDEX
    Explanations

    instances or mentions of relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.07
    4:0.08
    5:0.08
    6:0.07
    7:0.09
    8:0.08
    9:0.09
    10:0.08
    11:0.09
    Negative Logits
    RFC
    -3.12
    ailable
    -3.09
    DVD
    -3.04
    Closure
    -2.97
     induct
    -2.85
    emetery
    -2.76
    ogy
    -2.70
    istors
    -2.62
    STD
    -2.57
     Chennai
    -2.56
    POSITIVE LOGITS
     Batt
    2.61
    !--
    2.42
    eka
    2.39
     Bund
    2.37
    !
    2.35
    sat
    2.35
    cffffcc
    2.34
     Mech
    2.31
     Wow
    2.30
    sol
    2.29
    Activations Density 0.000%

    No Known Activations