Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11521
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal and criminal justice situations

    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
    0:0.06
    1:0.01
    2:0.05
    3:0.21
    4:0.02
    5:0.12
    6:0.02
    7:0.05
    8:0.02
    9:0.02
    10:0.34
    11:0.02
    Negative Logits
    erie
    -2.18
     endeav
    -2.14
    atography
    -2.12
    krit
    -2.03
    erning
    -1.96
    urat
    -1.92
    rupulous
    -1.86
    bill
    -1.85
    uminati
    -1.85
    focused
    -1.84
    POSITIVE LOGITS
     flaw
    2.94
     harm
    2.57
     defects
    2.53
    ERROR
    2.52
     irregularities
    2.48
     defect
    2.43
     ERROR
    2.39
     VIDEOS
    2.38
     outage
    2.35
     errors
    2.32
    Activations Density 0.016%

    No Known Activations