© 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. 10-ATT-KK
    11. 16113
    Prev
    Next
    INDEX
    Explanations

    references to mixed-use development projects and their associated features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.04
    2:0.05
    3:0.05
    4:0.20
    5:0.06
    6:0.03
    7:0.14
    8:0.04
    9:0.07
    10:0.04
    11:0.18
    Negative Logits
     fucked
    -2.67
     cunt
    -2.59
    fuck
    -2.57
     fuck
    -2.48
     dick
    -2.46
    Unknown
    -2.34
    acus
    -2.33
     bullshit
    -2.31
     damned
    -2.29
     bastard
    -2.25
    POSITIVE LOGITS
     landsc
    2.59
     expansive
    2.59
    rium
    2.49
     spacious
    2.45
     multip
    2.24
     integrated
    2.15
     overlook
    2.14
     revamped
    2.13
     redesigned
    2.13
     expanded
    2.10
    Activations Density 0.031%

    No Known Activations