© 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. 5-ATT-KK
    11. 44761
    Prev
    Next
    INDEX
    Explanations

    expressions related to agreements and emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.04
    3:0.04
    4:0.12
    5:0.04
    6:0.34
    7:0.14
    8:0.03
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
    gio
    -1.30
    ��
    -1.25
    ollo
    -1.25
    employed
    -1.21
     Aph
    -1.18
     trustworthy
    -1.16
     beverage
    -1.15
     Tud
    -1.15
    joining
    -1.14
    Versions
    -1.13
    POSITIVE LOGITS
    schild
    1.66
    obin
    1.43
    road
    1.42
     completion
    1.31
     Shotgun
    1.30
     裏�
    1.30
    pletion
    1.29
     Bangalore
    1.28
     Hague
    1.27
    owitz
    1.26
    Activations Density 0.009%

    No Known Activations