© 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. 42038
    Prev
    Next
    INDEX
    Explanations

    mentions of editorial content, specifically op-eds published in notable newspapers

    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
    2:0.09
    3:0.06
    4:0.12
    5:0.02
    6:0.07
    7:0.18
    8:0.03
    9:0.04
    10:0.21
    11:0.09
    Negative Logits
    meg
    -1.69
    variable
    -1.48
     CLSID
    -1.47
    kus
    -1.44
    packages
    -1.41
     allele
    -1.39
     hapl
    -1.34
     showers
    -1.33
     lag
    -1.33
     humidity
    -1.30
    POSITIVE LOGITS
    vertisement
    1.85
     aloud
    1.83
     endorsing
    1.62
     denouncing
    1.52
     behalf
    1.51
     advoc
    1.49
    ortium
    1.45
    uggest
    1.43
     titled
    1.42
    umenthal
    1.40
    Activations Density 0.003%

    No Known Activations