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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 11360
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific organizations and studies

    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
    1:0.04
    2:0.06
    3:0.24
    4:0.03
    5:0.04
    6:0.12
    7:0.17
    8:0.05
    9:0.03
    10:0.07
    11:0.07
    Negative Logits
    mere
    -1.30
    yout
    -1.26
     sneakers
    -1.25
     undone
    -1.25
    ammy
    -1.19
    eret
    -1.16
    ardless
    -1.14
     nood
    -1.08
     strangers
    -1.08
    jri
    -1.06
    POSITIVE LOGITS
     Telescope
    1.20
    phant
    1.19
    Sensor
    1.17
     Glac
    1.16
    Information
    1.14
    DEBUG
    1.13
    EMP
    1.12
    Technical
    1.11
     Sturgeon
    1.11
    FORMATION
    1.11
    Activations Density 0.007%

    No Known Activations