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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10731
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings and the burden of proof

    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
    1:0.02
    2:0.12
    3:0.15
    4:0.04
    5:0.34
    6:0.03
    7:0.06
    8:0.03
    9:0.03
    10:0.07
    11:0.02
    Negative Logits
     Deadline
    -2.69
    ��
    -2.63
     Renew
    -2.38
    arov
    -2.36
     laure
    -2.34
     Defenders
    -2.33
     Oversight
    -2.25
    cour
    -2.23
    olid
    -2.21
     ANN
    -2.16
    POSITIVE LOGITS
     raped
    2.73
     murdered
    2.71
    agate
    2.53
     vanished
    2.52
     abducted
    2.50
     robbery
    2.46
     kidnapped
    2.46
     rapes
    2.45
     faked
    2.44
     traffickers
    2.42
    Activations Density 0.306%

    No Known Activations