© 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. 12250
    Prev
    Next
    INDEX
    Explanations

    expressions of inability or limitation

    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
    0:0.28
    1:0.02
    2:0.12
    3:0.10
    4:0.03
    5:0.08
    6:0.03
    7:0.05
    8:0.05
    9:0.03
    10:0.15
    11:0.03
    Negative Logits
    ardless
    -2.59
    ench
    -2.48
    entially
    -2.31
     raiding
    -2.20
    lvl
    -2.13
    �
    -2.09
    geoning
    -2.06
     roof
    -2.04
    �
    -2.04
     stronghold
    -2.03
    POSITIVE LOGITS
     notebooks
    2.96
     memoir
    2.80
    writers
    2.73
    Write
    2.62
     autobiography
    2.51
     Rider
    2.50
    光
    2.45
     Writ
    2.44
     Journals
    2.42
    Writing
    2.42
    Activations Density 0.000%

    No Known Activations