© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 5729
    Prev
    Next
    INDEX
    Explanations

    occurrences of conditional statements and decisions regarding rights and laws

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.10
    1:0.02
    2:0.40
    3:0.10
    4:0.03
    5:0.07
    6:0.04
    7:0.04
    8:0.03
    9:0.04
    10:0.06
    11:0.02
    Negative Logits
     Osc
    -2.77
     comparisons
    -2.55
     Pik
    -2.52
     grap
    -2.43
     composite
    -2.39
    oscope
    -2.38
     dots
    -2.38
     accum
    -2.35
    stats
    -2.28
    average
    -2.26
    POSITIVE LOGITS
     refusal
    5.49
     refusing
    4.46
     request
    4.24
     refused
    4.16
     Request
    4.10
     objection
    4.07
     refuse
    4.07
     reluctance
    4.05
     unwillingness
    4.05
     acquies
    3.99
    Activations Density 1.027%

    No Known Activations