© 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. 7971
    Prev
    Next
    INDEX
    Explanations

    contexts involving hypothetical scenarios and the implications of actions or decisions

    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
    0:0.04
    1:0.03
    2:0.06
    3:0.29
    4:0.03
    5:0.06
    6:0.03
    7:0.07
    8:0.03
    9:0.03
    10:0.26
    11:0.02
    Negative Logits
     utmost
    -2.04
     patience
    -1.94
    bern
    -1.93
     congr
    -1.80
     celebr
    -1.79
     Tuesday
    -1.79
    pport
    -1.78
     Detail
    -1.75
    bourg
    -1.74
    Tuesday
    -1.73
    POSITIVE LOGITS
    "?
    3.04
    ?!"
    2.99
    !?"
    2.72
    ?".
    2.70
    )?
    2.67
    ?"
    2.58
    ...?
    2.55
     disappeared
    2.55
    ?!
    2.50
    ?",
    2.46
    Activations Density 0.016%

    No Known Activations