© 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. 13687
    Prev
    Next
    INDEX
    Explanations

    time-related terms, especially related to specific durations like "years" and "decade."

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.08
    1:0.03
    2:0.11
    3:0.08
    4:0.11
    5:0.11
    6:0.05
    7:0.03
    8:0.15
    9:0.07
    10:0.08
    11:0.04
    Negative Logits
    Thor
    -1.19
    Ut
    -1.03
    UCT
    -1.03
     Nib
    -1.03
     Doc
    -1.02
     resemb
    -1.01
    aba
    -1.00
    Sing
    -1.00
    Unique
    -1.00
    PE
    -1.00
    POSITIVE LOGITS
    imester
    1.65
    enium
    1.58
    generation
    1.32
    sembly
    1.30
     onslaught
    1.27
    isphere
    1.27
    ahime
    1.26
    insula
    1.26
     continents
    1.21
    grounds
    1.20
    Activations Density 0.024%

    No Known Activations