© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 17497
    Prev
    Next
    INDEX
    Explanations

    phrases related to critical societal issues and controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.05
    1:0.03
    2:0.04
    3:0.05
    4:0.04
    5:0.18
    6:0.01
    7:0.02
    8:0.42
    9:0.05
    10:0.04
    11:0.02
    Negative Logits
    isconsin
    -1.65
    agents
    -1.52
     pione
    -1.47
     newcom
    -1.45
     antidepressant
    -1.44
     Hancock
    -1.38
    xon
    -1.36
    thur
    -1.31
    imen
    -1.30
    senal
    -1.30
    POSITIVE LOGITS
    otom
    1.68
    ?!
    1.62
    !?
    1.59
     anyway
    1.52
    -.
    1.49
    TION
    1.49
    naires
    1.47
    naire
    1.44
     entails
    1.42
     anyways
    1.39
    Activations Density 0.798%

    No Known Activations