© 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. 19833
    Prev
    Next
    INDEX
    Explanations

    phrases concerning consent and privacy policy agreements

    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
    0:0.14
    1:0.03
    2:0.09
    3:0.09
    4:0.11
    5:0.17
    6:0.05
    7:0.08
    8:0.05
    9:0.02
    10:0.09
    11:0.03
    Negative Logits
     heavens
    -2.04
     hourly
    -1.96
     ceilings
    -1.86
     floors
    -1.84
     joints
    -1.83
     Benefits
    -1.81
     nails
    -1.76
     Commands
    -1.76
     conductor
    -1.71
     Built
    -1.71
    POSITIVE LOGITS
    ACY
    2.26
    DATA
    2.15
    Andre
    2.14
    bably
    2.12
    REDACTED
    2.10
    METHOD
    2.07
    odder
    2.00
    FORMATION
    1.96
    TERN
    1.92
    EStream
    1.91
    Activations Density 0.006%

    No Known Activations