© 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. 7831
    Prev
    Next
    INDEX
    Explanations

    content related to underground music culture and community events

    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
    0:0.16
    1:0.02
    2:0.18
    3:0.14
    4:0.03
    5:0.10
    6:0.05
    7:0.07
    8:0.11
    9:0.02
    10:0.03
    11:0.03
    Negative Logits
    Deploy
    -2.74
    iscal
    -2.64
    renheit
    -2.51
     Accountability
    -2.48
     Elections
    -2.45
    osate
    -2.39
    EPA
    -2.37
    Environmental
    -2.32
    uler
    -2.30
     HHS
    -2.29
    POSITIVE LOGITS
     DJs
    4.02
     genres
    3.94
     genre
    3.91
     funk
    3.79
     eclectic
    3.75
     psychedelic
    3.73
     techno
    3.70
     punk
    3.69
     rave
    3.63
     synth
    3.62
    Activations Density 0.251%

    No Known Activations