© 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. 1322
    Prev
    Next
    INDEX
    Explanations

    references to attributes related to abilities or characteristics

    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
    0:0.06
    1:0.07
    2:0.05
    3:0.09
    4:0.12
    5:0.22
    6:0.04
    7:0.09
    8:0.07
    9:0.04
    10:0.07
    11:0.03
    Negative Logits
    growth
    -2.47
     Profile
    -2.39
    ername
    -2.38
    Rank
    -2.38
    Skill
    -2.35
    Gender
    -2.32
     spelling
    -2.32
     NAME
    -2.30
    Loading
    -2.28
    MIN
    -2.23
    POSITIVE LOGITS
     extrad
    2.49
     Canaver
    2.48
     detective
    2.41
     stewards
    2.35
     aest
    2.34
     detectives
    2.31
     exped
    2.27
     interf
    2.26
     aesthetic
    2.24
    arnaev
    2.19
    Activations Density 0.000%

    No Known Activations