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. 112
    Prev
    Next
    INDEX
    Explanations

    elements related to criminal incidents and legal issues

    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
    0:0.08
    1:0.02
    2:0.07
    3:0.05
    4:0.06
    5:0.04
    6:0.22
    7:0.04
    8:0.06
    9:0.29
    10:0.02
    11:0.01
    Negative Logits
     Rw
    -3.61
     Metall
    -3.56
     Hung
    -3.53
     Horde
    -3.49
    Tre
    -3.38
    CN
    -3.35
    RON
    -3.30
     Villa
    -3.25
    pine
    -3.21
     McKin
    -3.20
    POSITIVE LOGITS
     Isaac
    10.32
    Isa
    8.41
     Isa
    6.36
    javascript
    4.47
     Abraham
    4.36
     ESC
    4.21
     Genesis
    4.19
     Bib
    4.14
     Isaiah
    4.14
     Bee
    3.79
    Activations Density 0.001%

    No Known Activations