© 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. 9-ATT-KK
    6. 11954
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to photography and shooting techniques

    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
    0:0.08
    1:0.03
    2:0.09
    3:0.04
    4:0.04
    5:0.03
    6:0.27
    7:0.02
    8:0.04
    9:0.26
    10:0.02
    11:0.03
    Negative Logits
     Drupal
    -3.93
     Dyn
    -3.85
    Roman
    -3.63
     Beckham
    -3.51
     Cornwall
    -3.48
     Cyborg
    -3.43
    ead
    -3.38
     Dominic
    -3.36
     Siem
    -3.35
    ester
    -3.29
    POSITIVE LOGITS
     Shot
    7.84
     Shoot
    7.64
     shooters
    7.58
     Shooter
    7.57
     shoot
    7.36
     shooting
    7.29
     Shots
    7.07
     shot
    7.05
     shooter
    7.03
     Shooting
    7.00
    Activations Density 0.024%

    No Known Activations