© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 23152
    Prev
    Next
    INDEX
    Explanations

    references to legal verdicts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words related to judicial decisions and legal outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.06
    2:0.09
    3:0.05
    4:0.12
    5:0.08
    6:0.04
    7:0.03
    8:0.09
    9:0.22
    10:0.07
    11:0.03
    Negative Logits
    otropic
    -1.63
    aceae
    -1.43
    flu
    -1.39
    sylv
    -1.37
    yi
    -1.34
    utical
    -1.29
    phia
    -1.29
    methyl
    -1.28
    adium
    -1.27
    si
    -1.27
    POSITIVE LOGITS
     Jury
    1.63
     verdict
    1.56
     Carney
    1.47
     Judgment
    1.42
     indictment
    1.41
     jurors
    1.39
     tribunal
    1.38
     Favor
    1.38
     Voters
    1.36
     Invalid
    1.36
    Activations Density 0.003%

    No Known Activations