© 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. 12917
    Prev
    Next
    INDEX
    Explanations

    phrases related to tabletop Role-Playing games, scientific fields, and military science fiction series

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

    terms related to firearms and military specifications

    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
    1:0.14
    2:0.08
    3:0.02
    4:0.04
    5:0.15
    6:0.07
    7:0.09
    8:0.07
    9:0.09
    10:0.09
    11:0.10
    Negative Logits
    )).
    -1.71
    ]).
    -1.54
    ))))
    -1.53
     trickle
    -1.48
    qus
    -1.47
    ))
    -1.45
    ��
    -1.40
    Correct
    -1.39
    ]."
    -1.38
    ��
    -1.38
    POSITIVE LOGITS
     combines
    1.39
     consists
    1.36
     nowadays
    1.34
    erenn
    1.32
     combining
    1.28
     inher
    1.28
     bestselling
    1.27
    formerly
    1.26
     Author
    1.24
    pires
    1.23
    Activations Density 0.387%

    No Known Activations