© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 8122
    Prev
    Next
    INDEX
    Explanations

    references to experimental methodology and statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.07
    2:0.17
    3:0.10
    4:0.05
    5:0.05
    6:0.07
    7:0.07
    8:0.13
    9:0.08
    10:0.07
    11:0.04
    Negative Logits
    ById
    -1.08
    nesday
    -0.99
    ة
    -0.96
    TextColor
    -0.96
     arrang
    -0.93
    rollers
    -0.92
     Strongh
    -0.92
    edIn
    -0.91
    ktop
    -0.88
     airs
    -0.85
    POSITIVE LOGITS
    )—
    1.23
    ),
    1.21
    ),"
    1.15
    ).[
    1.10
    )",
    1.10
    ).
    1.05
    )[
    1.01
    )),
    1.01
    ?),
    1.00
    !),
    0.98
    Activations Density 0.084%

    No Known Activations