© 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. 2-ATT-KK
    11. 13534
    Prev
    Next
    INDEX
    Explanations

    food items mentioned in a list

    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
    0:0.16
    1:0.03
    2:0.04
    3:0.11
    4:0.06
    5:0.09
    6:0.05
    7:0.07
    8:0.09
    9:0.06
    10:0.13
    11:0.07
    Negative Logits
    Russ
    -0.94
     Axel
    -0.91
     Hung
    -0.89
     Gork
    -0.87
     Falk
    -0.87
     Eugene
    -0.86
     Faces
    -0.86
     Ack
    -0.86
     Toro
    -0.86
     Rahman
    -0.85
    POSITIVE LOGITS
    depending
    1.40
     whichever
    1.35
    entimes
    1.34
    anything
    1.25
     thereof
    1.23
    elt
    1.12
    cffff
    1.05
    ilet
    1.01
    eco
    1.01
    ichever
    1.00
    Activations Density 0.244%

    No Known Activations