© 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. 19510
    Prev
    Next
    INDEX
    Explanations

    phrases related to accountability and consequences

    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
    1:0.05
    2:0.08
    3:0.16
    4:0.07
    5:0.08
    6:0.05
    7:0.10
    8:0.09
    9:0.04
    10:0.03
    11:0.14
    Negative Logits
     ­
    -4.23
    �
    -3.65
    ­
    -3.45
    "—
    -3.23
    .—
    -3.16
    —
    -3.16
    ē
    -3.15
    —"
    -3.15
    ‑
    -3.11
    Enlarge
    -3.04
    POSITIVE LOGITS
     didnt
    3.52
     alot
    3.43
     idiots
    3.40
     stupidity
    3.19
     HUGE
    3.09
     negro
    3.09
     doesnt
    3.06
     retarded
    3.02
     english
    2.99
     shitty
    2.83
    Activations Density 1.015%

    No Known Activations