© 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. 12470
    Prev
    Next
    INDEX
    Explanations

    references to societal issues and community dynamics

    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
    1:0.01
    2:0.03
    3:0.17
    4:0.01
    5:0.04
    6:0.02
    7:0.03
    8:0.03
    9:0.02
    10:0.54
    11:0.01
    Negative Logits
    idav
    -2.32
    ording
    -2.13
     refusing
    -2.03
    ignore
    -1.93
     Want
    -1.92
    allowed
    -1.88
     risking
    -1.87
     Wanted
    -1.83
     waiting
    -1.82
     choosing
    -1.82
    POSITIVE LOGITS
     into
    2.59
     onto
    2.50
     closer
    2.26
     together
    2.23
     reinforcements
    2.03
     improved
    2.01
     to
    2.00
     fame
    2.00
     unto
    1.98
     lessons
    1.95
    Activations Density 0.150%

    No Known Activations