© 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. 3-ATT-KK
    11. 10749
    Prev
    Next
    INDEX
    Explanations

    expressions related to self-harm and suicide

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.09
    3:0.09
    4:0.02
    5:0.03
    6:0.05
    7:0.10
    8:0.16
    9:0.17
    10:0.05
    11:0.13
    Negative Logits
    taboola
    -1.32
    glers
    -1.27
     Presents
    -1.23
    ciplinary
    -1.22
    CLUD
    -1.15
    published
    -1.12
    lished
    -1.08
    spect
    -1.06
    ══
    -1.05
    Statement
    -1.03
    POSITIVE LOGITS
     chunk
    1.15
     unborn
    1.15
     invaders
    1.10
     ego
    1.08
     damn
    1.08
     dro
    1.06
     crap
    1.06
     shit
    1.05
     pesky
    1.04
     goddamn
    1.03
    Activations Density 0.042%

    No Known Activations