© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 5946
    Prev
    Next
    INDEX
    Explanations

    instances of encouraging phrases about trying again or persevering

    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
    0:0.02
    1:0.10
    2:0.08
    3:0.05
    4:0.02
    5:0.13
    6:0.09
    7:0.10
    8:0.07
    9:0.09
    10:0.11
    11:0.08
    Negative Logits
    ォ
    -1.47
    Notice
    -1.25
    "(
    -1.16
     Rangers
    -1.15
    isons
    -1.14
    restrial
    -1.12
    kees
    -1.12
    arkable
    -1.11
    rists
    -1.10
     Barber
    -1.09
    POSITIVE LOGITS
     Cancel
    1.54
     captcha
    1.46
    )!
    1.40
     url
    1.35
    Browser
    1.30
     redistributed
    1.28
    )</
    1.27
     Gmail
    1.24
     Downloads
    1.24
     Email
    1.22
    Activations Density 0.002%

    No Known Activations