© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 2826
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to computer hardware and performance capabilities

    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
    2:0.11
    3:0.14
    4:0.02
    5:0.37
    6:0.02
    7:0.04
    8:0.04
    9:0.02
    10:0.05
    11:0.03
    Negative Logits
     manufacturer
    -3.48
     Manufacturer
    -3.34
     defective
    -3.32
    manufact
    -3.22
    ufact
    -3.18
     silicon
    -3.15
     Specifications
    -3.14
    士
    -3.11
    bolt
    -3.04
    Connector
    -3.03
    POSITIVE LOGITS
     anthropology
    3.41
     dungeons
    3.35
     lectures
    3.35
     scenes
    3.20
     movies
    3.20
     Anthrop
    3.08
     sermon
    3.04
     editing
    3.02
     chores
    2.96
     prose
    2.93
    Activations Density 0.239%

    No Known Activations