© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 10910
    Prev
    Next
    INDEX
    Explanations

    names and identifiers

    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
    3:0.34
    4:0.03
    5:0.02
    6:0.04
    7:0.14
    8:0.05
    9:0.09
    10:0.05
    11:0.05
    Negative Logits
    theless
    -1.67
     Stout
    -1.53
    enhagen
    -1.49
     vomit
    -1.46
     CTR
    -1.40
    glers
    -1.32
     skelet
    -1.26
     drown
    -1.22
     drowning
    -1.21
     drowned
    -1.19
    POSITIVE LOGITS
    utical
    1.69
    Lago
    1.48
    ��
    1.46
     Lumpur
    1.43
    nai
    1.35
    jee
    1.33
    )\
    1.30
     Puzzles
    1.28
     Parish
    1.26
     Pradesh
    1.26
    Activations Density 0.012%

    No Known Activations