© 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. 20842
    Prev
    Next
    INDEX
    Explanations

    references to statistical or numerical data related to rankings

    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
    1:0.32
    2:0.02
    3:0.06
    4:0.04
    5:0.20
    6:0.06
    7:0.04
    8:0.04
    9:0.03
    10:0.02
    11:0.07
    Negative Logits
    caster
    -2.88
    CAST
    -2.75
    join
    -2.66
    said
    -2.65
    rx
    -2.64
    ▬
    -2.64
    ttle
    -2.60
     KN
    -2.57
    Refer
    -2.56
    twitter
    -2.54
    POSITIVE LOGITS
     pristine
    2.88
     Sanctuary
    2.66
    ogun
    2.59
    ocene
    2.49
     unforgettable
    2.49
     priests
    2.48
     Goodbye
    2.45
     priesthood
    2.45
     Guatemala
    2.44
     inspectors
    2.41
    Activations Density 0.000%

    No Known Activations