© 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. 10-ATT-KK
    11. 20414
    Prev
    Next
    INDEX
    Explanations

    references to financial misconduct and regulatory issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.01
    2:0.03
    3:0.05
    4:0.12
    5:0.35
    6:0.04
    7:0.04
    8:0.01
    9:0.21
    10:0.01
    11:0.04
    Negative Logits
    Hopefully
    -3.65
    Alright
    -3.49
     Hopefully
    -3.36
     tomorrow
    -3.31
    apest
    -3.19
     🙂
    -3.08
    Tomorrow
    -3.07
     NOW
    -3.02
     hopefully
    -3.02
    Anyway
    -2.97
    POSITIVE LOGITS
     improperly
    4.59
     inappropriately
    4.36
     violated
    4.31
     breached
    3.83
     unlawfully
    3.76
     improper
    3.70
     alleging
    3.68
     illegally
    3.68
     mishand
    3.65
     tainted
    3.62
    Activations Density 1.026%

    No Known Activations