© 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. 10-ATT-KK
    11. 8810
    Prev
    Next
    INDEX
    Explanations

    admissions of mistakes or confessions related to wrongdoing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.07
    2:0.02
    3:0.07
    4:0.14
    5:0.06
    6:0.13
    7:0.24
    8:0.02
    9:0.05
    10:0.04
    11:0.06
    Negative Logits
     Absent
    -2.63
    actionDate
    -2.34
     entreprene
    -2.25
     Effective
    -2.16
    seless
    -2.15
     Ender
    -2.13
     Recommend
    -2.12
     Needs
    -2.11
     Cheap
    -2.09
    URRENT
    -2.03
    POSITIVE LOGITS
     confessed
    2.79
     admitting
    2.67
     admitted
    2.65
     confess
    2.65
     admits
    2.49
     admit
    2.43
     confession
    2.34
     retracted
    2.33
    ML
    2.11
     denied
    2.07
    Activations Density 0.039%

    No Known Activations