© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 23153
    Prev
    Next
    INDEX
    Explanations

    attention-grabbing phrases, quotes, or statements in text

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

    content that discusses attention, judgment, and the act of drawing distinctions or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.01
    2:0.24
    3:0.10
    4:0.04
    5:0.05
    6:0.02
    7:0.01
    8:0.28
    9:0.11
    10:0.03
    11:0.01
    Negative Logits
     wors
    -1.17
    lov
    -1.16
    ONSORED
    -1.14
     operated
    -1.13
    SPONSORED
    -1.11
     Mead
    -1.11
     Antar
    -1.08
    aceae
    -1.06
    esi
    -1.06
     Eater
    -1.06
    POSITIVE LOGITS
    udo
    1.42
    zig
    1.31
    ugs
    1.19
     conclusions
    1.19
    usk
    1.18
    edo
    1.15
    haar
    1.14
    bern
    1.14
    undo
    1.11
    umbn
    1.11
    Activations Density 0.019%

    No Known Activations