© 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. 4397
    Prev
    Next
    INDEX
    Explanations

    negatively connoted terms relating to emotional distress or hardship

    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
    1:0.02
    2:0.03
    3:0.06
    4:0.03
    5:0.04
    6:0.05
    7:0.03
    8:0.02
    9:0.07
    10:0.05
    11:0.51
    Negative Logits
     «
    -3.79
    Newsletter
    -3.54
     »
    -3.50
     ­
    -3.40
     ::
    -2.99
     ―
    -2.97
     �
    -2.88
    luent
    -2.88
    »
    -2.73
     nil
    -2.71
    POSITIVE LOGITS
    /
    8.40
    /(
    6.77
    /,
    6.65
    ./
    6.52
    )/
    6.45
    /_
    6.31
    /-
    6.30
    /.
    6.20
    /"
    6.18
    /)
    5.99
    Activations Density 0.107%

    No Known Activations