© 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. 4257
    Prev
    Next
    INDEX
    Explanations

    titles of songs and song-related content

    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
    0:0.03
    1:0.04
    2:0.02
    3:0.05
    4:0.03
    5:0.05
    6:0.04
    7:0.04
    8:0.10
    9:0.02
    10:0.03
    11:0.48
    Negative Logits
     
    -3.46
    UK
    -3.12
    )...
    -3.09
    isations
    -3.03
     UKIP
    -2.96
    BBC
    -2.92
    …
    -2.88
    Ireland
    -2.84
    Mrs
    -2.76
    ...
    -2.76
    POSITIVE LOGITS
     ―
    8.07
    .>>
    5.24
     [/
    4.77
    >]
    4.75
     �
    4.72
     |--
    4.62
     |
    4.59
     [...]
    4.47
     ·
    4.37
     }}
    4.33
    Activations Density 0.002%

    No Known Activations