© 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 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. 9762
    Prev
    Next
    INDEX
    Explanations

    attributes and qualifications of experts in various fields

    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
    1:0.07
    2:0.07
    3:0.03
    4:0.07
    5:0.32
    6:0.05
    7:0.05
    8:0.08
    9:0.05
    10:0.08
    11:0.05
    Negative Logits
     persisted
    -2.30
    )).
    -2.20
    ��
    -2.02
    ��
    -2.00
    itored
    -1.96
    ��
    -1.94
    thora
    -1.89
     futile
    -1.89
    ]).
    -1.88
    �
    -1.88
    POSITIVE LOGITS
     Entreprene
    2.03
     Founder
    1.97
    quartered
    1.94
     inher
    1.91
    enegger
    1.85
     internationally
    1.82
     accelerator
    1.80
     Colleg
    1.79
     specializes
    1.79
     descendant
    1.77
    Activations Density 0.654%

    No Known Activations