© 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. 25155
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values and statistics related to various subjects

    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
    0:0.08
    1:0.01
    2:0.11
    3:0.06
    4:0.14
    5:0.02
    6:0.16
    7:0.03
    8:0.09
    9:0.05
    10:0.06
    11:0.13
    Negative Logits
    comm
    -1.12
     Replay
    -1.07
    heart
    -1.04
    uses
    -1.01
     squads
    -1.00
     OpenGL
    -1.00
     GUI
    -0.99
    dri
    -0.99
    CRE
    -0.99
     baker
    -0.99
    POSITIVE LOGITS
    CLASSIFIED
    1.35
    ONSORED
    1.32
    ドラゴン
    1.31
     tiss
    1.27
    regor
    1.20
     hemor
    1.20
     SECTION
    1.19
    VERTIS
    1.19
    ——
    1.18
    ichever
    1.17
    Activations Density 0.002%

    No Known Activations