© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 598
    Prev
    Next
    INDEX
    Explanations

    phrases indicating health-related issues and conditions

    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
    0:0.03
    1:0.02
    2:0.09
    3:0.20
    4:0.02
    5:0.11
    6:0.03
    7:0.31
    8:0.06
    9:0.02
    10:0.04
    11:0.02
    Negative Logits
    ():
    -2.41
    perse
    -2.32
    Begin
    -2.29
    begin
    -2.12
    >[
    -2.09
    utherford
    -2.06
    animous
    -2.06
    lite
    -1.99
    upon
    -1.99
    lets
    -1.98
    POSITIVE LOGITS
     incarceration
    2.91
     criminal
    2.72
     addiction
    2.53
     homelessness
    2.53
     schooling
    2.51
     criminality
    2.47
     infections
    2.46
     disabilities
    2.45
     crime
    2.41
     allergies
    2.40
    Activations Density 0.036%

    No Known Activations