© 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. 18064
    Prev
    Next
    INDEX
    Explanations

    instances of strong emotional expressions or critiques surrounding individuals in a political context

    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
    1:0.41
    2:0.04
    3:0.05
    4:0.03
    5:0.03
    6:0.09
    7:0.04
    8:0.01
    9:0.11
    10:0.06
    11:0.03
    Negative Logits
    older
    -3.02
    old
    -2.85
    farious
    -2.78
    interstitial
    -2.68
    visors
    -2.63
    odd
    -2.46
    Known
    -2.40
     trick
    -2.40
     advant
    -2.35
     older
    -2.34
    POSITIVE LOGITS
     totally
    6.17
     completely
    6.06
     absolutely
    5.46
    completely
    5.42
     Totally
    5.21
    absolutely
    5.10
    Absolutely
    5.09
     Absolutely
    5.03
     entirely
    5.00
     utterly
    4.69
    Activations Density 0.030%

    No Known Activations