© 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. 3-ATT-KK
    11. 6837
    Prev
    Next
    INDEX
    Explanations

    sections that involve citations or references in a text

    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
    0:0.03
    1:0.09
    2:0.13
    3:0.05
    4:0.04
    5:0.05
    6:0.08
    7:0.08
    8:0.10
    9:0.17
    10:0.05
    11:0.08
    Negative Logits
    aryn
    -1.23
    roit
    -1.15
     unsus
    -1.08
    VB
    -1.06
    ogram
    -1.03
     bend
    -1.02
    vd
    -1.01
    milo
    -1.00
     OPEN
    -0.99
    wig
    -0.98
    POSITIVE LOGITS
     showc
    1.31
    ONSORED
    1.23
     settlers
    1.20
     Surviv
    1.17
    laughter
    1.17
    enei
    1.15
    ']
    1.12
    }}}
    1.09
     interference
    1.08
    "],
    1.07
    Activations Density 0.017%

    No Known Activations