© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 12118
    Prev
    Next
    INDEX
    Explanations

    strong action verbs typically associated with investigative or critical commentary

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    verbs that indicate events or actions with significance or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.08
    2:0.24
    3:0.02
    4:0.02
    5:0.03
    6:0.09
    7:0.18
    8:0.10
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
    asia
    -1.02
    steamapps
    -0.99
    ixel
    -0.98
    Mos
    -0.97
    razil
    -0.97
    jab
    -0.95
    zie
    -0.94
    ttes
    -0.93
    assador
    -0.93
     Whip
    -0.92
    POSITIVE LOGITS
     happens
    1.13
    RGB
    1.09
    pires
    1.08
     inspires
    1.04
     transpired
    1.03
    FML
    1.00
     prevents
    1.00
     OpenGL
    0.93
     happened
    0.93
     comprises
    0.93
    Activations Density 0.037%

    No Known Activations