© 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. 11992
    Prev
    Next
    INDEX
    Explanations

    mentions of blame and accountability 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
    0:0.12
    1:0.02
    2:0.08
    3:0.09
    4:0.03
    5:0.06
    6:0.06
    7:0.07
    8:0.31
    9:0.04
    10:0.03
    11:0.03
    Negative Logits
     Akron
    -4.34
     Osaka
    -4.34
     Hussein
    -4.01
     Milwaukee
    -3.91
     Fuji
    -3.85
     Cleveland
    -3.75
     Pacers
    -3.70
     Birmingham
    -3.70
     Durham
    -3.69
     Giul
    -3.64
    POSITIVE LOGITS
     EVE
    8.50
     CCP
    7.32
     Ships
    4.94
     fleets
    4.91
     ships
    4.85
     corp
    4.74
     ship
    4.58
     starship
    4.54
     Cald
    4.38
     pilots
    4.30
    Activations Density 0.010%

    No Known Activations