© 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. 5-ATT-KK
    11. 40446
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions or feelings

    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
    0:0.04
    1:0.03
    2:0.05
    3:0.06
    4:0.03
    5:0.12
    6:0.03
    7:0.03
    8:0.28
    9:0.08
    10:0.13
    11:0.08
    Negative Logits
    apter
    -1.66
    idd
    -1.62
     Mub
    -1.61
    cott
    -1.57
    UCT
    -1.45
    NetMessage
    -1.42
    urious
    -1.38
     weap
    -1.37
     incorpor
    -1.37
    ————
    -1.36
    POSITIVE LOGITS
    nesday
    1.46
    ecided
    1.42
    icultural
    1.41
     Photographer
    1.39
    wegian
    1.38
    anian
    1.33
     VICE
    1.31
    sections
    1.31
    azo
    1.31
     Eminem
    1.30
    Activations Density 0.233%

    No Known Activations