© 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. 3-ATT-KK
    11. 14091
    Prev
    Next
    INDEX
    Explanations

    events or actions happening consecutively or in close succession

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

    phrases indicating time transitions and sequencing events

    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
    0:0.02
    1:0.04
    2:0.12
    3:0.14
    4:0.02
    5:0.03
    6:0.13
    7:0.07
    8:0.05
    9:0.12
    10:0.11
    11:0.11
    Negative Logits
     somehow
    -1.05
    ively
    -1.04
    ulia
    -1.02
     aloud
    -0.99
     anew
    -0.97
    /.
    -0.94
    owed
    -0.94
    stats
    -0.85
     artificially
    -0.85
    rather
    -0.84
    POSITIVE LOGITS
    icz
    1.07
     exting
    1.06
    velength
    1.02
     裏�
    0.95
     NX
    0.94
    ieth
    0.93
    ITNESS
    0.90
     ├
    0.88
     ├──
    0.88
    ILLE
    0.87
    Activations Density 0.006%

    No Known Activations