© 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. 22143
    Prev
    Next
    INDEX
    Explanations

    mentions of Howard University and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.07
    1:0.03
    2:0.25
    3:0.10
    4:0.09
    5:0.06
    6:0.03
    7:0.03
    8:0.02
    9:0.16
    10:0.07
    11:0.03
    Negative Logits
    Saharan
    -1.44
    Fed
    -1.27
    onomous
    -1.21
    devices
    -1.20
    Contents
    -1.17
    Higher
    -1.14
    ccording
    -1.13
    eworthy
    -1.10
    Unix
    -1.10
    yx
    -1.08
    POSITIVE LOGITS
    mith
    1.36
     Jr
    1.34
    ERSON
    1.24
     Zimmer
    1.22
    kinson
    1.20
    ovich
    1.20
    erson
    1.19
    Jr
    1.07
    heim
    1.06
     Sr
    1.06
    Activations Density 0.006%

    No Known Activations