© 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. 9-ATT-KK
    11. 23286
    Prev
    Next
    INDEX
    Explanations

    common phrases and expressions related to opinions and personal sentiments

    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
    0:0.06
    1:0.04
    2:0.07
    3:0.34
    4:0.05
    5:0.05
    6:0.02
    7:0.06
    8:0.04
    9:0.03
    10:0.17
    11:0.02
    Negative Logits
     comb
    -2.03
    ilateral
    -1.92
    ascript
    -1.92
    letal
    -1.81
    arial
    -1.79
    urrent
    -1.73
    azines
    -1.73
     triangular
    -1.69
     incapac
    -1.69
    irted
    -1.67
    POSITIVE LOGITS
    ?!
    3.52
    ...?
    3.09
    !?
    2.97
    ?),
    2.85
    ?!"
    2.68
    )?
    2.67
    ?
    2.60
     yours
    2.58
    !),
    2.56
    ?).
    2.51
    Activations Density 0.315%

    No Known Activations