© 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. 21190
    Prev
    Next
    INDEX
    Explanations

    quotations or statements made by individuals

    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
    0:0.02
    1:0.03
    2:0.02
    3:0.03
    4:0.13
    5:0.03
    6:0.13
    7:0.10
    8:0.13
    9:0.05
    10:0.02
    11:0.25
    Negative Logits
    >:
    -2.87
    .):
    -2.79
    イト
    -2.74
    .:
    -2.70
    =]
    -2.67
    '/
    -2.65
    ]:
    -2.64
    igslist
    -2.57
    ICLE
    -2.51
    ��
    -2.51
    POSITIVE LOGITS
     Tasman
    3.48
     Tasmania
    3.33
     £
    3.29
     licence
    3.21
     Queensland
    3.13
     Cardiff
    3.13
     Auckland
    3.06
     licences
    3.06
     Constable
    3.05
     Canberra
    3.02
    Activations Density 0.109%

    No Known Activations