© 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. 42504
    Prev
    Next
    INDEX
    Explanations

    references to a specific AI technology company and its offerings

    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
    0:0.02
    1:0.03
    2:0.05
    3:0.04
    4:0.03
    5:0.06
    6:0.10
    7:0.02
    8:0.03
    9:0.06
    10:0.43
    11:0.07
    Negative Logits
    hower
    -2.47
    cair
    -1.98
    ersion
    -1.80
     wre
    -1.77
    aughters
    -1.76
    olate
    -1.72
     haun
    -1.71
    obyl
    -1.69
     retreat
    -1.69
    anus
    -1.67
    POSITIVE LOGITS
     messaging
    2.04
    online
    2.03
     Transparency
    1.92
    Wiki
    1.89
     clipboard
    1.88
     emoji
    1.85
     subtitles
    1.81
     NXT
    1.81
    Chan
    1.77
    Voice
    1.77
    Activations Density 0.000%

    No Known Activations