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

    Neuronpedia

    Jacobian LensNEW
    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. 13191
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate refusal or resistance to actions or requests

    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
    0:0.04
    1:0.02
    2:0.06
    3:0.21
    4:0.02
    5:0.14
    6:0.02
    7:0.06
    8:0.03
    9:0.02
    10:0.32
    11:0.02
    Negative Logits
     envy
    -2.35
     uncanny
    -2.19
     success
    -2.01
     coinc
    -1.98
     inexper
    -1.94
     coincidence
    -1.93
    ocre
    -1.93
     phenomenal
    -1.92
     misunderstanding
    -1.89
     Success
    -1.88
    POSITIVE LOGITS
     contraceptives
    2.24
     vaccinations
    2.19
     burial
    2.16
     treatments
    2.06
    enance
    2.06
     treatment
    2.02
    atories
    1.99
     screenings
    1.98
     concessions
    1.98
     vaccines
    1.95
    Activations Density 0.144%

    No Known Activations