© 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. 2-ATT-KK
    11. 13471
    Prev
    Next
    INDEX
    Explanations

    references to different types of topics, such as news, technology, politics, and general descriptions of places or events

    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
    0:0.07
    1:0.01
    2:0.22
    3:0.07
    4:0.10
    5:0.09
    6:0.02
    7:0.05
    8:0.12
    9:0.05
    10:0.10
    11:0.05
    Negative Logits
    reviewed
    -1.38
    wine
    -1.20
    aneers
    -1.16
    Reviewed
    -1.13
    wart
    -1.12
    upon
    -1.10
    ワ
    -1.10
    enment
    -1.05
    mith
    -1.05
    oso
    -1.05
    POSITIVE LOGITS
     horizon
    1.27
    entanyl
    1.12
     proportions
    1.09
    aturday
    1.07
    _-_
    1.00
    oneliness
    0.99
     billboards
    0.98
     motivations
    0.98
     clipboard
    0.96
    NetMessage
    0.96
    Activations Density 0.114%

    No Known Activations