© 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. 6300
    Prev
    Next
    INDEX
    Explanations

    references to social issues and systemic problems related to crime and victim support

    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
    0:0.05
    1:0.03
    2:0.11
    3:0.19
    4:0.07
    5:0.20
    6:0.05
    7:0.09
    8:0.03
    9:0.03
    10:0.06
    11:0.04
    Negative Logits
    sembly
    -2.28
    selage
    -2.17
    Army
    -2.08
    Company
    -2.04
     sailed
    -1.99
    NASA
    -1.98
     Gundam
    -1.96
     Mech
    -1.96
     Farmer
    -1.93
    Cola
    -1.90
    POSITIVE LOGITS
     offenders
    3.44
     perpetrators
    2.96
     abusers
    2.91
     offender
    2.87
     prevention
    2.79
     culprit
    2.74
     victims
    2.60
     prevalence
    2.59
     incidents
    2.54
     detection
    2.52
    Activations Density 0.876%

    No Known Activations