© 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. 2-ATT-KK
    11. 22709
    Prev
    Next
    INDEX
    Explanations

    text related to legal matters and governmental actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    quantitative measurements or comparisons in relation to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.02
    2:0.14
    3:0.09
    4:0.04
    5:0.16
    6:0.04
    7:0.06
    8:0.09
    9:0.07
    10:0.12
    11:0.05
    Negative Logits
    estyles
    -1.25
    uds
    -1.05
    istries
    -1.04
    azeera
    -1.02
    ibles
    -1.02
    inis
    -1.00
    plet
    -0.98
    qt
    -0.97
    DAQ
    -0.95
    itudes
    -0.94
    POSITIVE LOGITS
    ���
    1.08
    nob
    1.08
     conflic
    1.06
     )]
    0.98
     Protective
    0.93
    "))
    0.93
     "…
    0.93
    ritical
    0.91
     "[
    0.90
    ESA
    0.90
    Activations Density 0.380%

    No Known Activations