© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 21378
    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
    0:0.07
    1:0.07
    2:0.08
    3:0.08
    4:0.08
    5:0.08
    6:0.07
    7:0.09
    8:0.08
    9:0.06
    10:0.08
    11:0.09
    Negative Logits
    amera
    -1.44
     android
    -1.41
     UW
    -1.40
     UCLA
    -1.39
     Ober
    -1.38
     Neural
    -1.31
     UCS
    -1.30
     Eps
    -1.27
     SCP
    -1.26
     VK
    -1.25
    POSITIVE LOGITS
    liam
    1.51
    spin
    1.51
     prosecutions
    1.45
     reckoning
    1.44
    yssey
    1.43
    bah
    1.40
    responsible
    1.40
     Hodg
    1.39
    icion
    1.39
    advertising
    1.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.