© 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. 5-ATT-KK
    11. 27956
    Prev
    Next
    INDEX
    Explanations

    active verbs that indicate significant emotional or physical actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.05
    1:0.02
    2:0.10
    3:0.09
    4:0.06
    5:0.02
    6:0.28
    7:0.12
    8:0.05
    9:0.02
    10:0.07
    11:0.06
    Negative Logits
     Jav
    -1.55
     Hemp
    -1.38
     designation
    -1.31
     filing
    -1.31
     Cham
    -1.31
     sake
    -1.30
     Sham
    -1.25
     Mandatory
    -1.24
     Jah
    -1.24
     Xavier
    -1.22
    POSITIVE LOGITS
    etheless
    1.92
     grav
    1.89
    ench
    1.73
     uncontroll
    1.60
    ulty
    1.55
     downwards
    1.50
    ynes
    1.50
    blems
    1.49
    kered
    1.49
    ract
    1.47
    Activations Density 0.016%

    No Known Activations