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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28398
    Prev
    Next
    INDEX
    Explanations

    phrases indicating accusations or blame

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.05
    3:0.13
    4:0.04
    5:0.03
    6:0.02
    7:0.40
    8:0.02
    9:0.05
    10:0.09
    11:0.10
    Negative Logits
    ipeg
    -1.79
    ebook
    -1.64
     Feast
    -1.50
     Kardash
    -1.50
     Jagu
    -1.46
    apore
    -1.46
    books
    -1.44
    acl
    -1.40
    Flo
    -1.40
    stakes
    -1.39
    POSITIVE LOGITS
     sabot
    1.92
     hypocrisy
    1.88
     negligence
    1.83
     unethical
    1.77
     sabotage
    1.77
     wrongdoing
    1.73
     complicity
    1.70
     improper
    1.69
     mishand
    1.68
     misuse
    1.68
    Activations Density 0.020%

    No Known Activations