© 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. 37652
    Prev
    Next
    INDEX
    Explanations

    references to public figures and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.02
    2:0.08
    3:0.35
    4:0.05
    5:0.10
    6:0.01
    7:0.02
    8:0.04
    9:0.12
    10:0.09
    11:0.05
    Negative Logits
    ゴン
    -1.89
    aired
    -1.54
    ギ
    -1.51
    ヤ
    -1.49
    later
    -1.48
    ruary
    -1.47
     ):
    -1.45
    odox
    -1.45
     Lydia
    -1.44
    ortium
    -1.44
    POSITIVE LOGITS
    ,"
    3.54
    ..."
    3.42
    ,'"
    3.35
    ),"
    3.24
    ,''
    3.11
    .,"
    3.07
    %"
    3.01
    )"
    2.97
     [
    2.96
     …"
    2.93
    Activations Density 1.063%

    No Known Activations