© 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. 15550
    Prev
    Next
    INDEX
    Explanations

    references to object characteristics, specifically their status and visibility in certain contexts

    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
    0:0.23
    1:0.03
    2:0.20
    3:0.11
    4:0.03
    5:0.08
    6:0.04
    7:0.07
    8:0.05
    9:0.04
    10:0.04
    11:0.02
    Negative Logits
    amacare
    -2.52
     slog
    -2.38
     Rollins
    -2.37
     Saturdays
    -2.37
     Zeal
    -2.36
     McA
    -2.35
     relapse
    -2.35
     Sundays
    -2.34
     Reb
    -2.33
    otide
    -2.27
    POSITIVE LOGITS
     Objects
    5.10
     objects
    4.89
    objects
    4.63
     object
    4.07
    object
    3.41
    Object
    3.40
     deform
    3.30
     Properties
    3.12
    properties
    3.10
    property
    2.96
    Activations Density 0.049%

    No Known Activations