© 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. 9-ATT-KK
    11. 24301
    Prev
    Next
    INDEX
    Explanations

    terms related to legal convictions and innocence

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.02
    2:0.37
    3:0.06
    4:0.03
    5:0.09
    6:0.03
    7:0.08
    8:0.04
    9:0.05
    10:0.05
    11:0.03
    Negative Logits
    Monitor
    -2.48
    ヤ
    -2.44
    threatening
    -2.37
     Feder
    -2.37
     Typh
    -2.37
    threat
    -2.36
     Slack
    -2.33
     interruption
    -2.24
    ebus
    -2.23
    闘
    -2.23
    POSITIVE LOGITS
     acquitted
    4.74
     exoner
    4.66
     conviction
    4.56
     convict
    4.48
     innocence
    4.36
     verdict
    4.34
     Guilty
    4.19
     convictions
    4.16
     guilty
    4.09
     convicted
    3.98
    Activations Density 0.034%

    No Known Activations