© 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. 20158
    Prev
    Next
    INDEX
    Explanations

    instances of commentary on societal behavior and attitudes

    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
    1:0.03
    2:0.05
    3:0.09
    4:0.08
    5:0.08
    6:0.02
    7:0.05
    8:0.19
    9:0.02
    10:0.04
    11:0.25
    Negative Logits
    .'
    -6.57
    ,'
    -6.44
    .'"
    -6.23
    )'
    -5.90
    ,'"
    -5.82
    !'
    -5.36
    ?'
    -5.21
    :'
    -4.99
    !'"
    -4.54
    ?'"
    -4.53
    POSITIVE LOGITS
    ��極
    3.84
     "
    3.83
     ",
    3.77
     ".
    3.77
     "+
    3.35
     £
    3.31
     "@
    3.30
     "-
    3.21
     "_
    3.20
     BBC
    3.17
    Activations Density 0.021%

    No Known Activations