© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43599
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.06
    3:0.12
    4:0.05
    5:0.07
    6:0.03
    7:0.03
    8:0.05
    9:0.18
    10:0.22
    11:0.08
    Negative Logits
    Favorite
    -1.12
    ゴ
    -1.04
    ゼウス
    -1.04
    Born
    -1.03
     Entered
    -1.03
    NAME
    -1.03
    UES
    -1.00
     Selected
    -0.97
    ointment
    -0.97
    reetings
    -0.96
    POSITIVE LOGITS
     deterrent
    1.24
     mitigation
    1.20
     mitigating
    1.18
     moot
    1.15
     loopholes
    1.14
     deterrence
    1.13
     anecdotal
    1.13
     hazard
    1.10
     situational
    1.03
     policing
    1.02
    Activations Density 1.736%

    No Known Activations