Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11500
    Prev
    Next
    INDEX
    Explanations

    information about numerical data, particularly statistics and rankings related to sports 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
    0:0.05
    1:0.04
    2:0.05
    3:0.09
    4:0.06
    5:0.09
    6:0.07
    7:0.07
    8:0.04
    9:0.03
    10:0.07
    11:0.28
    Negative Logits
    …………
    -3.16
    ';
    -3.13
    .</
    -3.04
     …"
    -2.97
     oun
    -2.96
    .:
    -2.89
    『
    -2.88
     toget
    -2.87
    :'
    -2.85
     proble
    -2.80
    POSITIVE LOGITS
     -
    5.80
    ](
    2.90
     "-
    2.75
     �
    2.71
    )--
    2.61
    arthed
    2.58
     )
    2.56
     --
    2.53
    )...
    2.39
     ---
    2.32
    Activations Density 0.006%

    No Known Activations