© 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. 10-ATT-KK
    11. 8940
    Prev
    Next
    INDEX
    Explanations

    various programming and coding constructs or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.07
    2:0.10
    3:0.05
    4:0.07
    5:0.16
    6:0.07
    7:0.06
    8:0.05
    9:0.15
    10:0.06
    11:0.06
    Negative Logits
     doubtful
    -2.33
     Frazier
    -2.33
     stricken
    -2.31
     refuted
    -2.19
     ineligible
    -2.16
     ridden
    -2.15
     contradicted
    -2.13
     disputed
    -2.10
     rocked
    -2.08
     Harrison
    -2.07
    POSITIVE LOGITS
    import
    3.44
    ¶
    3.40
    License
    3.16
    Configuration
    3.15
    Usage
    3.13
    Creating
    3.09
    Debug
    3.01
    Requirements
    2.98
     ):
    2.98
    Using
    2.97
    Activations Density 0.067%

    No Known Activations