© 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. 22179
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    1:0.05
    2:0.07
    3:0.12
    4:0.06
    5:0.17
    6:0.05
    7:0.06
    8:0.08
    9:0.09
    10:0.09
    11:0.05
    Negative Logits
     FANTASY
    -1.42
    meric
    -1.20
    Congratulations
    -1.19
    bilt
    -1.13
     Surviv
    -1.10
    ------------------------------------------------
    -1.09
     Kenobi
    -1.09
     Umb
    -1.08
     Loren
    -1.06
    SPEC
    -1.05
    POSITIVE LOGITS
     Carbuncle
    1.16
    eus
    1.13
     deval
    1.08
     faults
    1.06
    tesy
    1.04
    rone
    1.03
    urger
    1.02
     redes
    1.01
    ‎
    1.01
    Topic
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.