© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 17852
    Prev
    Next
    INDEX
    Explanations

    statistical data and percentages related to surveys and polls

    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
    0:0.03
    1:0.01
    2:0.06
    3:0.12
    4:0.03
    5:0.14
    6:0.06
    7:0.04
    8:0.02
    9:0.04
    10:0.31
    11:0.08
    Negative Logits
     anytime
    -2.41
     backlog
    -2.37
    terday
    -2.32
    recent
    -2.22
    Hours
    -2.04
    Cooldown
    -1.97
     decades
    -1.96
     lately
    -1.94
    hours
    -1.88
    Until
    -1.88
    POSITIVE LOGITS
    %).
    2.31
    %)
    2.30
    ).[
    2.15
     favour
    2.04
    ')
    1.99
    ').
    1.91
    )",
    1.89
    ameron
    1.87
    )\
    1.85
     Gors
    1.82
    Activations Density 0.009%

    No Known Activations