© 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. 12212
    Prev
    Next
    INDEX
    Explanations

    information related to physical exercise and fitness

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

    specific punctuation and formatting used in written text

    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
    0:0.10
    1:0.07
    2:0.06
    3:0.03
    4:0.11
    5:0.06
    6:0.08
    7:0.06
    8:0.12
    9:0.08
    10:0.10
    11:0.06
    Negative Logits
    acco
    -1.16
     Rodrig
    -1.15
     ].
    -1.15
    .).
    -1.10
    rys
    -1.08
     peacefully
    -1.08
     ],
    -1.07
    .)
    -1.06
     ).
    -1.04
     prosec
    -1.03
    POSITIVE LOGITS
     Quantity
    1.11
     Designer
    1.08
     Kubrick
    1.07
     Offline
    1.05
     Genius
    1.05
     Context
    1.02
    Focus
    1.00
    abase
    0.97
     Duration
    0.97
    Developer
    0.97
    Activations Density 0.102%

    No Known Activations