© 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. 10105
    Prev
    Next
    INDEX
    Explanations

    references to child abuse within institutional contexts

    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
    0:0.13
    1:0.02
    2:0.27
    3:0.09
    4:0.03
    5:0.11
    6:0.04
    7:0.06
    8:0.10
    9:0.02
    10:0.03
    11:0.04
    Negative Logits
     barric
    -2.62
     Hawking
    -2.44
    Dispatch
    -2.43
     Ü
    -2.41
     Kers
    -2.39
     checkpoints
    -2.36
     windshield
    -2.34
     Bullets
    -2.28
    �
    -2.28
     checkpoint
    -2.28
    POSITIVE LOGITS
     pedoph
    4.73
     paed
    4.73
     grooming
    3.75
     abusers
    3.74
     abused
    3.51
     abusing
    3.45
     indecent
    3.24
    abuse
    3.17
     underage
    3.16
     abuse
    3.13
    Activations Density 0.029%

    No Known Activations