© 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. 7929
    Prev
    Next
    INDEX
    Explanations

    frequent mentions of validation, orders, and concerns in a legal or regulatory 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
    0:0.05
    1:0.02
    2:0.06
    3:0.31
    4:0.03
    5:0.06
    6:0.02
    7:0.05
    8:0.02
    9:0.02
    10:0.30
    11:0.01
    Negative Logits
    aunts
    -2.43
    classes
    -2.41
    arers
    -2.40
    rones
    -2.34
    mates
    -2.32
     mates
    -2.28
    faces
    -2.19
     Lists
    -2.16
    keys
    -2.16
    isons
    -2.16
    POSITIVE LOGITS
     possibility
    3.07
     ambiguity
    2.55
     unanim
    2.53
     inconsistency
    2.49
     complication
    2.48
     heterogeneity
    2.47
    ossibility
    2.42
     overlap
    2.35
     disparity
    2.35
     happening
    2.33
    Activations Density 0.334%

    No Known Activations