© 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. 18964
    Prev
    Next
    INDEX
    Explanations

    the end of sentences

    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
    0:0.05
    1:0.13
    2:0.05
    3:0.06
    4:0.03
    5:0.07
    6:0.03
    7:0.04
    8:0.12
    9:0.03
    10:0.07
    11:0.26
    Negative Logits
    ".[
    -5.11
     (£
    -4.10
     £
    -3.92
     Whilst
    -3.79
     criticised
    -3.69
     whilst
    -3.62
    ‑
    -3.61
    ).[
    -3.54
     Nato
    -3.50
    etheless
    -3.38
    POSITIVE LOGITS
    ...
    3.68
     --
    3.33
    JUST
    3.24
    ..."
    3.18
    Dallas
    3.00
    Photos
    2.97
     docs
    2.75
     })
    2.66
    CBC
    2.66
     »
    2.62
    Activations Density 0.000%

    No Known Activations