© 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. 46577
    Prev
    Next
    INDEX
    Explanations

    language related to controversial statements and their 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
    1:0.01
    2:0.07
    3:0.06
    4:0.05
    5:0.04
    6:0.02
    7:0.04
    8:0.04
    9:0.05
    10:0.43
    11:0.11
    Negative Logits
     colonies
    -1.86
     ladder
    -1.73
     Libre
    -1.66
     colony
    -1.66
     tel
    -1.59
     Grid
    -1.59
     Tel
    -1.58
    itia
    -1.57
     rebuild
    -1.57
     hiber
    -1.56
    POSITIVE LOGITS
    uggest
    2.35
    milo
    1.95
     misrepresent
    1.89
    ueless
    1.88
    laughter
    1.87
     disrespectful
    1.87
     purported
    1.86
     uttered
    1.82
     sincere
    1.81
     insulting
    1.78
    Activations Density 0.113%

    No Known Activations