© 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. 5-ATT-KK
    11. 45209
    Prev
    Next
    INDEX
    Explanations

    specific names and entities associated with investigations and legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.02
    2:0.06
    3:0.09
    4:0.07
    5:0.16
    6:0.02
    7:0.03
    8:0.06
    9:0.20
    10:0.18
    11:0.05
    Negative Logits
     [|
    -1.49
     lear
    -1.29
    Electric
    -1.18
    ratom
    -1.16
    ⓘ
    -1.14
     bicycl
    -1.14
    rug
    -1.11
     learners
    -1.11
    ogram
    -1.09
     cycl
    -1.09
    POSITIVE LOGITS
    ��
    1.37
     contended
    1.23
     accuser
    1.23
     vehemently
    1.19
     contend
    1.17
     purported
    1.16
     accused
    1.16
    withstanding
    1.15
     tarn
    1.14
     vetoed
    1.13
    Activations Density 1.084%

    No Known Activations