© 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. 12560
    Prev
    Next
    INDEX
    Explanations

    legal terms and decisions

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

    modal verbs that indicate possibility, necessity, or obligation

    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
    0:0.05
    1:0.03
    2:0.20
    3:0.03
    4:0.03
    5:0.09
    6:0.12
    7:0.12
    8:0.05
    9:0.04
    10:0.09
    11:0.11
    Negative Logits
     stances
    -1.65
    ernels
    -1.58
     partnerships
    -1.45
    headers
    -1.43
     margins
    -1.42
     venues
    -1.39
    lees
    -1.38
     divisions
    -1.38
     motions
    -1.37
     Houses
    -1.37
    POSITIVE LOGITS
    ogram
    1.41
     Called
    1.32
    tenance
    1.28
     existed
    1.24
     consisting
    1.22
    ictionary
    1.22
     resembling
    1.20
     composed
    1.19
    older
    1.19
    ridge
    1.18
    Activations Density 0.181%

    No Known Activations