© 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. 1357
    Prev
    Next
    INDEX
    Explanations

    references to emotional trauma and loss

    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
    0:0.05
    1:0.02
    2:0.17
    3:0.30
    4:0.03
    5:0.11
    6:0.02
    7:0.07
    8:0.06
    9:0.02
    10:0.06
    11:0.02
    Negative Logits
     innovations
    -2.22
     unveiling
    -2.19
     incorporation
    -2.15
     elabor
    -2.11
     diffusion
    -2.08
     variants
    -2.03
     chiefly
    -2.02
     traditionally
    -2.00
     modernization
    -1.96
     incorporating
    -1.96
    POSITIVE LOGITS
     abuser
    2.96
     hurting
    2.84
     raped
    2.81
     fucked
    2.77
     coward
    2.76
     hurt
    2.76
     blackmail
    2.75
     rape
    2.73
     innocent
    2.62
     innocence
    2.58
    Activations Density 1.060%

    No Known Activations