© 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. 9-ATT-KK
    11. 9159
    Prev
    Next
    INDEX
    Explanations

    instances of emphatic statements or exclamations in the text

    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
    0:0.04
    1:0.01
    2:0.03
    3:0.08
    4:0.11
    5:0.08
    6:0.03
    7:0.05
    8:0.18
    9:0.01
    10:0.02
    11:0.31
    Negative Logits
    !'
    -4.17
    )'
    -3.93
    ']
    -3.77
    [/
    -3.76
    ]'
    -3.69
    ?'
    -3.66
    ')
    -3.61
    !]
    -3.58
    ?]
    -3.46
    =]
    -3.06
    POSITIVE LOGITS
     "
    3.31
     "+
    3.24
     £
    3.11
     ".
    3.08
     UKIP
    3.07
     "_
    2.89
     ",
    2.85
     Tube
    2.85
     RAF
    2.77
    Shape
    2.70
    Activations Density 0.016%

    No Known Activations