© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 7099
    Prev
    Next
    INDEX
    Explanations

    phrases related to existential necessity and social issues

    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
    0:0.03
    1:0.02
    2:0.06
    3:0.19
    4:0.02
    5:0.05
    6:0.02
    7:0.05
    8:0.02
    9:0.02
    10:0.46
    11:0.02
    Negative Logits
    Myth
    -2.70
    Aren
    -2.19
    named
    -2.06
     baseless
    -2.03
    into
    -2.01
    ogyn
    -1.94
    Initialized
    -1.91
    gross
    -1.91
    annot
    -1.91
     wrongful
    -1.90
    POSITIVE LOGITS
     urgently
    3.82
     ASAP
    2.83
     urgent
    2.82
     refuel
    2.75
     refres
    2.71
     recomp
    2.54
     replen
    2.52
     recharge
    2.48
     help
    2.47
     preferably
    2.43
    Activations Density 0.334%

    No Known Activations