© 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. 3-ATT-KK
    11. 5201
    Prev
    Next
    INDEX
    Explanations

    image or photo-related descriptions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.09
    2:0.13
    3:0.05
    4:0.04
    5:0.05
    6:0.12
    7:0.08
    8:0.08
    9:0.06
    10:0.14
    11:0.08
    Negative Logits
    soType
    -1.02
     Coins
    -0.98
     conceive
    -0.86
     Runtime
    -0.84
     defe
    -0.82
    ¢
    -0.81
    ITNESS
    -0.80
    ploma
    -0.79
    daq
    -0.78
     Errors
    -0.78
    POSITIVE LOGITS
    lik
    1.05
    jar
    0.87
    icularly
    0.83
    aron
    0.81
     toug
    0.81
     conspicuous
    0.80
    vec
    0.80
    alis
    0.79
    umably
    0.75
    central
    0.75
    Activations Density 0.071%

    No Known Activations