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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 9957
    Prev
    Next
    INDEX
    Explanations

    discussions around significant buildings or structures, particularly cathedrals

    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
    0:0.03
    1:0.02
    2:0.07
    3:0.28
    4:0.05
    5:0.05
    6:0.02
    7:0.02
    8:0.06
    9:0.13
    10:0.13
    11:0.08
    Negative Logits
    '."
    -2.38
    ".[
    -2.29
    ''.
    -2.28
    .''.
    -2.20
    ascript
    -2.08
    ."[
    -2.06
    "}
    -1.98
    .'"
    -1.94
    RESULTS
    -1.94
    ".
    -1.93
    POSITIVE LOGITS
     premise
    1.58
    paralle
    1.53
    eaturing
    1.51
     dystopian
    1.42
     staple
    1.39
    latable
    1.37
    erenn
    1.36
     arguably
    1.36
     famed
    1.34
     dudes
    1.31
    Activations Density 0.784%

    No Known Activations