© 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. 6357
    Prev
    Next
    INDEX
    Explanations

    numerical and categorical data related to entities such as locations, companies, and organizations

    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
    1:0.04
    2:0.06
    3:0.02
    4:0.01
    5:0.08
    6:0.10
    7:0.10
    8:0.04
    9:0.03
    10:0.07
    11:0.38
    Negative Logits
    SpaceEngineers
    -1.51
     prompt
    -1.41
    otto
    -1.36
    ega
    -1.32
     causation
    -1.30
    ndra
    -1.29
     Zeit
    -1.28
    hai
    -1.28
    edia
    -1.27
    ounters
    -1.27
    POSITIVE LOGITS
     apiece
    2.20
     totaling
    2.08
     Including
    2.02
     crammed
    1.73
    total
    1.72
     total
    1.70
    覚醒
    1.59
     including
    1.56
    including
    1.52
    utes
    1.51
    Activations Density 0.775%

    No Known Activations