© 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. 23220
    Prev
    Next
    INDEX
    Explanations

    information related to specific events like sport competitions, political actions, tragedies, and community efforts

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

    references to groups of people or entities and their characteristics

    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
    0:0.05
    1:0.02
    2:0.09
    3:0.26
    4:0.05
    5:0.09
    6:0.04
    7:0.06
    8:0.04
    9:0.11
    10:0.10
    11:0.05
    Negative Logits
    \\\\\\\\
    -1.05
    english
    -1.04
    jured
    -1.01
     Courier
    -0.98
     Eag
    -0.96
     cannabin
    -0.94
    NEWS
    -0.91
    quant
    -0.91
    Ted
    -0.90
     Annie
    -0.90
    POSITIVE LOGITS
    isphere
    1.76
    esta
    1.12
    odes
    1.10
    oran
    1.07
    born
    1.07
    iatus
    1.06
    anes
    1.03
    azeera
    0.99
    swick
    0.98
    oggle
    0.98
    Activations Density 0.130%

    No Known Activations