© 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. 23122
    Prev
    Next
    INDEX
    Explanations

    statements made by different speakers

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

    words indicating speech or declarations

    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
    0:0.07
    1:0.03
    2:0.16
    3:0.09
    4:0.10
    5:0.09
    6:0.05
    7:0.05
    8:0.05
    9:0.10
    10:0.09
    11:0.05
    Negative Logits
     outing
    -1.16
     disadvant
    -1.14
    bang
    -1.13
    uma
    -1.09
    zona
    -1.08
     unin
    -1.06
    iture
    -1.04
    geries
    -1.02
    ocracy
    -1.00
    clave
    -1.00
    POSITIVE LOGITS
    lycer
    1.39
    ️
    1.24
    者
    1.22
    ritten
    1.19
    respective
    1.19
    CAR
    1.15
     SUPPORT
    1.12
     :=
    1.11
    LESS
    1.11
    negie
    1.10
    Activations Density 0.207%

    No Known Activations