© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21335
    Prev
    Next
    INDEX
    Explanations

    occurrences where a person is speaking about specific events or topics

    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
    0:0.10
    1:0.06
    2:0.05
    3:0.07
    4:0.04
    5:0.06
    6:0.13
    7:0.04
    8:0.17
    9:0.11
    10:0.09
    11:0.03
    Negative Logits
     expended
    -1.36
    .''.
    -1.21
     nonviolent
    -1.15
     $$
    -1.13
    boro
    -1.12
     Moderate
    -1.12
    stood
    -1.08
     sacrific
    -1.08
     utilized
    -1.07
     1903
    -1.07
    POSITIVE LOGITS
    sound
    1.31
    audio
    1.31
    DIT
    1.30
    ispers
    1.27
    Talking
    1.27
    lique
    1.24
    Leaks
    1.21
    rompt
    1.20
    QUI
    1.20
    Desk
    1.20
    Activations Density 0.025%

    No Known Activations