© 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. 12638
    Prev
    Next
    INDEX
    Explanations

    phrases and identifiers related to organizations, actions, or conditions affecting societal 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
    0:0.05
    1:0.41
    2:0.05
    3:0.05
    4:0.03
    5:0.04
    6:0.07
    7:0.04
    8:0.03
    9:0.08
    10:0.06
    11:0.03
    Negative Logits
    ividual
    -2.60
    �
    -2.58
    cause
    -2.53
     Sometimes
    -2.45
    ership
    -2.44
    idity
    -2.42
    Sometimes
    -2.36
    frames
    -2.36
    soType
    -2.31
    eca
    -2.29
    POSITIVE LOGITS
     far
    5.63
    far
    4.88
     FAR
    3.79
     farther
    3.70
    much
    3.52
     nearer
    3.44
    Far
    3.30
     near
    3.21
    qus
    3.21
     Far
    3.11
    Activations Density 0.009%

    No Known Activations