© 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. 2-ATT-KK
    11. 21327
    Prev
    Next
    INDEX
    Explanations

    events or occurrences related to investigations, incidents, or criminal activities

    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
    0:0.06
    1:0.06
    2:0.09
    3:0.06
    4:0.05
    5:0.09
    6:0.04
    7:0.04
    8:0.06
    9:0.28
    10:0.09
    11:0.04
    Negative Logits
    joice
    -1.49
    heit
    -1.44
    veland
    -1.38
    brand
    -1.33
    THER
    -1.28
     cabinets
    -1.27
    onest
    -1.25
    haps
    -1.23
    minecraft
    -1.21
     Nord
    -1.19
    POSITIVE LOGITS
     aggravated
    1.47
    tesy
    1.38
     injuring
    1.36
     Officer
    1.33
     Mahm
    1.27
     conclud
    1.27
     severity
    1.27
     complainant
    1.26
     awa
    1.26
     vandalism
    1.25
    Activations Density 0.050%

    No Known Activations