© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 19476
    Prev
    Next
    INDEX
    Explanations

    references to political or financial controversies and allegations of misconduct

    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
    0:0.03
    1:0.02
    2:0.06
    3:0.36
    4:0.10
    5:0.06
    6:0.02
    7:0.04
    8:0.04
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
    )?
    -2.25
    erker
    -1.93
    )}
    -1.84
    )|
    -1.83
    )!
    -1.82
    ?),
    -1.78
    ?'
    -1.78
     ))
    -1.78
    Fed
    -1.74
     ours
    -1.73
    POSITIVE LOGITS
     stereotypical
    1.65
     whereas
    1.62
     disproportionately
    1.60
     concentrating
    1.53
     progressively
    1.48
     accumulated
    1.45
     possessing
    1.45
     seated
    1.43
     "…
    1.43
     unlawfully
    1.42
    Activations Density 0.748%

    No Known Activations