© 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. 3-ATT-KK
    11. 12345
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and procedural matters, such as legal actions, complaints, investigations, and publicizing

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

    phrases related to limitations and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.04
    2:0.14
    3:0.05
    4:0.02
    5:0.03
    6:0.07
    7:0.03
    8:0.13
    9:0.12
    10:0.11
    11:0.17
    Negative Logits
    icion
    -0.91
    started
    -0.90
     isn
    -0.89
    Fig
    -0.89
    oir
    -0.88
    tty
    -0.86
    Kings
    -0.85
    vs
    -0.85
     Tough
    -0.85
     wasn
    -0.85
    POSITIVE LOGITS
     nor
    1.71
     anymore
    1.62
     any
    1.17
     whatsoever
    1.15
     slightest
    1.10
    �
    1.04
     anybody
    1.03
     anything
    1.03
     Cheong
    1.02
     anywhere
    1.01
    Activations Density 0.086%

    No Known Activations