© 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. 11590
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "how."

    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
    0:0.04
    1:0.04
    2:0.14
    3:0.04
    4:0.03
    5:0.07
    6:0.09
    7:0.10
    8:0.08
    9:0.10
    10:0.13
    11:0.10
    Negative Logits
    ittee
    -1.31
    legate
    -1.15
    iya
    -1.14
    utch
    -1.10
    clave
    -1.10
    ocrat
    -1.09
    itol
    -1.07
    isha
    -1.07
    von
    -1.05
    alone
    -1.05
    POSITIVE LOGITS
     paths
    1.30
     meanings
    1.26
     assignments
    1.24
     parameters
    1.22
     formulas
    1.20
     timelines
    1.16
     caus
    1.15
     path
    1.13
     hypotheses
    1.13
     concepts
    1.11
    Activations Density 0.079%

    No Known Activations