© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43006
    Prev
    Next
    INDEX
    Explanations

    phrases indicating synchronization or harmony among groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.01
    2:0.08
    3:0.08
    4:0.09
    5:0.03
    6:0.02
    7:0.40
    8:0.03
    9:0.05
    10:0.06
    11:0.08
    Negative Logits
    raq
    -2.41
    qus
    -2.03
    acht
    -1.84
    brids
    -1.73
    urable
    -1.58
    uably
    -1.57
    uable
    -1.53
    prus
    -1.52
    metics
    -1.49
    reenshots
    -1.49
    POSITIVE LOGITS
     Remain
    1.59
     oppos
    1.53
     Eid
    1.43
     Sons
    1.28
     subsistence
    1.28
     Arkham
    1.27
     waking
    1.27
     SAN
    1.27
     ACTIONS
    1.27
     fare
    1.27
    Activations Density 0.000%

    No Known Activations