© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10777
    Prev
    Next
    INDEX
    Explanations

    phrases related to interactions and prompts for verification or confirmation

    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
    0:0.17
    1:0.02
    2:0.17
    3:0.18
    4:0.03
    5:0.06
    6:0.03
    7:0.09
    8:0.08
    9:0.01
    10:0.08
    11:0.02
    Negative Logits
     Tend
    -2.10
     negotiators
    -2.01
    hunt
    -2.01
     deliberations
    -2.00
     oranges
    -1.93
    wives
    -1.92
     Leaders
    -1.90
     agendas
    -1.89
     priorit
    -1.84
     Directors
    -1.84
    POSITIVE LOGITS
     login
    2.40
    registered
    2.19
    raud
    2.18
    Error
    2.17
    serial
    2.09
    error
    2.08
     Error
    2.08
    email
    2.07
     verification
    2.06
     Login
    2.06
    Activations Density 0.006%

    No Known Activations