© 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. 9-ATT-KK
    11. 2024
    Prev
    Next
    INDEX
    Explanations

    numerical and symbolic representations related to events or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.18
    1:0.05
    2:0.05
    3:0.12
    4:0.06
    5:0.05
    6:0.08
    7:0.06
    8:0.08
    9:0.04
    10:0.04
    11:0.15
    Negative Logits
     trooper
    -2.62
     cooper
    -2.42
    Texas
    -2.21
     CFL
    -2.21
     Levi
    -2.20
     informant
    -2.19
     Alberta
    -2.19
     improperly
    -2.18
     NASL
    -2.16
     flawed
    -2.16
    POSITIVE LOGITS
    �
    6.35
    �
    5.99
    4.27
        
    4.03
     �
    4.00
                    
    3.98
            
    3.75
    ........
    3.56
     �
    3.45
    ................
    3.38
    Activations Density 0.000%

    No Known Activations