© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 19816
    Prev
    Next
    INDEX
    Explanations

    greetings and welcomes within a community context

    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
    0:0.13
    1:0.02
    2:0.09
    3:0.26
    4:0.05
    5:0.10
    6:0.02
    7:0.06
    8:0.03
    9:0.01
    10:0.13
    11:0.04
    Negative Logits
     bulldo
    -2.15
     culp
    -2.03
     stunts
    -1.99
     rapists
    -1.99
     rapes
    -1.98
     convictions
    -1.98
     veto
    -1.98
     executions
    -1.94
     clauses
    -1.93
     decap
    -1.93
    POSITIVE LOGITS
    reetings
    2.97
     Welcome
    2.33
    elcome
    2.31
     Patreon
    2.31
    wave
    2.22
    ruary
    2.21
     Readers
    2.19
     Horizons
    2.17
    iatus
    2.14
    isode
    2.11
    Activations Density 0.119%

    No Known Activations