© 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. 11253
    Prev
    Next
    INDEX
    Explanations

    references to movement or direction

    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
    0:0.01
    1:0.02
    2:0.19
    3:0.16
    4:0.01
    5:0.02
    6:0.04
    7:0.07
    8:0.07
    9:0.24
    10:0.06
    11:0.05
    Negative Logits
    cu
    -1.38
    iqueness
    -1.22
     dy
    -1.06
    lime
    -1.06
     willingness
    -1.05
     fem
    -1.05
     sake
    -1.03
    worth
    -1.02
     dich
    -1.02
    iasm
    -1.00
    POSITIVE LOGITS
     Tours
    1.24
     Pandora
    1.21
     unch
    1.15
    EStream
    1.11
     Streaming
    1.07
     Alert
    1.05
    stanbul
    1.04
     Observatory
    1.04
     SOLD
    1.03
     Written
    1.02
    Activations Density 0.017%

    No Known Activations