© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 11117
    Prev
    Next
    INDEX
    Explanations

    metadata related to blog entries and publication information

    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
    0:0.18
    1:0.02
    2:0.07
    3:0.13
    4:0.07
    5:0.14
    6:0.04
    7:0.10
    8:0.07
    9:0.02
    10:0.09
    11:0.02
    Negative Logits
     loudspe
    -2.35
     perf
    -2.34
     demonstrating
    -2.22
     witness
    -2.11
     viol
    -2.06
     recordings
    -2.06
     orchestr
    -2.05
     pian
    -2.04
     separately
    -2.01
     specification
    -2.01
    POSITIVE LOGITS
     Canad
    2.14
     Gast
    2.09
    loo
    2.06
    Jet
    2.06
    atchewan
    1.97
    isure
    1.94
     Nova
    1.93
    ipeg
    1.91
     Leth
    1.87
     Winnipeg
    1.85
    Activations Density 0.001%

    No Known Activations