© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 41329
    Prev
    Next
    INDEX
    Explanations

    references to recovery and operations in critical situations

    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
    0:0.03
    1:0.02
    2:0.07
    3:0.17
    4:0.07
    5:0.09
    6:0.05
    7:0.06
    8:0.06
    9:0.16
    10:0.10
    11:0.08
    Negative Logits
    ague
    -1.74
    clus
    -1.63
     opio
    -1.53
     collegiate
    -1.53
     Wagner
    -1.44
    ogan
    -1.42
    agonists
    -1.40
    eco
    -1.40
    án
    -1.39
    ikan
    -1.39
    POSITIVE LOGITS
    )",
    2.15
    )].
    2.13
    ),"
    2.05
    ')
    1.99
    )]
    1.97
    )."
    1.97
    )</
    1.93
    %);
    1.87
    %]
    1.81
    )...
    1.81
    Activations Density 0.001%

    No Known Activations