© 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. 8371
    Prev
    Next
    INDEX
    Explanations

    negative assessments or doubt regarding safety and credibility

    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
    0:0.05
    1:0.01
    2:0.06
    3:0.19
    4:0.04
    5:0.05
    6:0.09
    7:0.05
    8:0.04
    9:0.09
    10:0.22
    11:0.05
    Negative Logits
     Fore
    -2.25
     Prospect
    -2.17
     Disaster
    -2.15
     recently
    -2.12
     Timber
    -2.11
     Ev
    -2.10
    Mis
    -1.96
     Stewart
    -1.94
    Mos
    -1.94
     contingency
    -1.91
    POSITIVE LOGITS
     anymore
    3.02
     anything
    3.00
     anybody
    2.87
    anything
    2.81
     ANY
    2.67
     anywhere
    2.48
     fuckin
    2.36
     darn
    2.32
     slightest
    2.29
    uckland
    2.27
    Activations Density 0.069%

    No Known Activations