© 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. 18001
    Prev
    Next
    INDEX
    Explanations

    key concepts related to societal issues and events

    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
    2:0.08
    3:0.25
    4:0.02
    5:0.05
    6:0.02
    7:0.04
    8:0.02
    9:0.02
    10:0.36
    11:0.02
    Negative Logits
     firsthand
    -2.24
     beforehand
    -2.07
    ufact
    -1.96
     resolves
    -1.96
     equivalents
    -1.89
    bis
    -1.86
    ullivan
    -1.85
    sequent
    -1.80
     previous
    -1.80
     subsequent
    -1.77
    POSITIVE LOGITS
    ?!
    2.42
    ?!"
    2.39
    ?".
    2.25
    !?"
    2.19
    ?」
    2.17
    !?
    2.17
    ?]
    2.12
    ?",
    2.12
    "?
    2.12
    )?
    1.97
    Activations Density 0.064%

    No Known Activations