© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19263
    Prev
    Next
    INDEX
    Explanations

    references to emergency responses and incidents related to fires

    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
    0:0.10
    1:0.01
    2:0.39
    3:0.09
    4:0.03
    5:0.10
    6:0.04
    7:0.06
    8:0.04
    9:0.03
    10:0.02
    11:0.01
    Negative Logits
     transsexual
    -3.15
    TPP
    -2.98
    plom
    -2.97
    ilateral
    -2.83
     bisexual
    -2.75
     bilateral
    -2.72
     neocons
    -2.70
     implants
    -2.70
    ploma
    -2.67
    osexual
    -2.59
    POSITIVE LOGITS
     flames
    5.64
     blaze
    5.62
     firefighters
    5.53
     arson
    5.44
     fires
    5.05
     charred
    5.00
     fire
    4.96
     extingu
    4.80
     wildfire
    4.73
     burned
    4.72
    Activations Density 0.244%

    No Known Activations