© 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. 5-ATT-KK
    11. 27730
    Prev
    Next
    INDEX
    Explanations

    instances of negative commentary or criticisms about societal issues, particularly regarding gender and violence

    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
    0:0.02
    1:0.02
    2:0.10
    3:0.07
    4:0.17
    5:0.02
    6:0.17
    7:0.14
    8:0.03
    9:0.03
    10:0.08
    11:0.09
    Negative Logits
    BuyableInstoreAndOnline
    -1.71
    isSpecialOrderable
    -1.55
    okane
    -1.52
    Reviewed
    -1.47
    enthal
    -1.38
    Spot
    -1.37
    izons
    -1.36
     Parkway
    -1.34
    zeb
    -1.31
    eele
    -1.31
    POSITIVE LOGITS
     nonsense
    1.54
     tricks
    1.49
     syll
    1.47
     backwards
    1.47
     Bastard
    1.44
     notation
    1.40
    ]}
    1.36
    amn
    1.36
    .'"
    1.35
     misc
    1.35
    Activations Density 0.001%

    No Known Activations