© 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. 7070
    Prev
    Next
    INDEX
    Explanations

    phrases related to the long-term implications of actions or decisions

    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
    1:0.03
    2:0.14
    3:0.14
    4:0.02
    5:0.03
    6:0.14
    7:0.08
    8:0.08
    9:0.07
    10:0.06
    11:0.13
    Negative Logits
    ÍÍ
    -1.61
     DRAG
    -1.38
    ODY
    -1.37
    wered
    -1.33
    OIL
    -1.31
    ォ
    -1.31
    _-
    -1.29
    OSE
    -1.27
    WER
    -1.26
    MSN
    -1.25
    POSITIVE LOGITS
     bracket
    1.51
     timeframe
    1.47
     preceding
    1.43
     cycle
    1.41
     trenches
    1.38
     universe
    1.38
     confines
    1.37
     realm
    1.37
     arena
    1.35
     era
    1.35
    Activations Density 0.004%

    No Known Activations