© 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. 2-ATT-KK
    11. 14730
    Prev
    Next
    INDEX
    Explanations

    phrases related to causes of events, deaths, or actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.02
    2:0.17
    3:0.03
    4:0.32
    5:0.08
    6:0.02
    7:0.01
    8:0.09
    9:0.09
    10:0.04
    11:0.02
    Negative Logits
    tle
    -1.99
    yss
    -1.68
    ump
    -1.63
    rown
    -1.57
    asking
    -1.56
    ceptive
    -1.54
    auder
    -1.54
    ebus
    -1.50
    uthor
    -1.50
    col
    -1.49
    POSITIVE LOGITS
     Leone
    1.56
     resemblance
    1.50
     outbreaks
    1.44
     experimentation
    1.41
     Khan
    1.40
     heterogeneity
    1.39
     physic
    1.39
     contamination
    1.37
     outbreak
    1.37
     illness
    1.35
    Activations Density 0.011%

    No Known Activations