© 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. 13373
    Prev
    Next
    INDEX
    Explanations

    words related to legal processes or proceedings

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

    terms related to processes and procurement in organizational contexts

    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
    1:0.04
    2:0.07
    3:0.25
    4:0.03
    5:0.03
    6:0.08
    7:0.07
    8:0.04
    9:0.10
    10:0.08
    11:0.11
    Negative Logits
    este
    -1.38
    ��
    -1.37
    onom
    -1.28
    igans
    -1.17
    olves
    -1.15
    hots
    -1.15
    eele
    -1.14
    vae
    -1.13
    inki
    -1.11
    anova
    -1.09
    POSITIVE LOGITS
     arrang
    1.30
     ACTIONS
    1.28
     WATCHED
    1.12
    task
    1.12
     dinner
    1.09
     �
    1.09
     ce
    1.06
     respons
    1.04
    ..........
    1.03
     Pact
    1.03
    Activations Density 0.002%

    No Known Activations