© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 23044
    Prev
    Next
    INDEX
    Explanations

    descriptions or evaluations using a comparison

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases that start with "but" indicating contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.02
    2:0.09
    3:0.08
    4:0.09
    5:0.12
    6:0.10
    7:0.03
    8:0.11
    9:0.07
    10:0.10
    11:0.05
    Negative Logits
    Ore
    -1.07
    Kill
    -0.99
    Planet
    -0.98
    cko
    -0.95
    itutes
    -0.92
    Medium
    -0.92
    $$$$
    -0.92
    Assembly
    -0.92
    Mesh
    -0.91
    SourceFile
    -0.91
    POSITIVE LOGITS
     nonetheless
    1.27
    etheless
    1.20
     conclud
    1.16
     concedes
    1.13
     msec
    1.12
     acknow
    1.04
     persisted
    1.01
     cautioned
    1.01
     abruptly
    1.01
     conced
    0.99
    Activations Density 0.146%

    No Known Activations