© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 11884
    Prev
    Next
    INDEX
    Explanations

    negative events or situations related to legal or medical issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    adjectives and phrases that convey negative or critical sentiments

    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
    0:0.04
    1:0.11
    2:0.17
    3:0.05
    4:0.03
    5:0.04
    6:0.13
    7:0.07
    8:0.05
    9:0.04
    10:0.06
    11:0.15
    Negative Logits
    schild
    -1.34
    eatures
    -1.30
    anwhile
    -1.29
     streng
    -1.29
    aston
    -1.06
     aptly
    -1.05
    CHO
    -1.05
     wisely
    -1.05
    chel
    -1.05
     ende
    -1.04
    POSITIVE LOGITS
    ",
    1.97
    "?
    1.90
    "
    1.89
    "—
    1.88
    ".
    1.84
    ":
    1.82
    ".[
    1.67
    "…
    1.65
    "),
    1.64
    "[
    1.63
    Activations Density 0.060%

    No Known Activations