© 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. 9-ATT-KK
    11. 4714
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and segments

    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
    0:0.04
    1:0.02
    2:0.04
    3:0.05
    4:0.04
    5:0.03
    6:0.12
    7:0.02
    8:0.03
    9:0.51
    10:0.02
    11:0.02
    Negative Logits
    ּ
    -3.37
     Camden
    -3.20
    awn
    -3.09
     Athena
    -3.05
     crow
    -3.04
    ocratic
    -3.04
    ocrates
    -2.96
     Sharon
    -2.96
     Athens
    -2.96
    Raven
    -2.92
    POSITIVE LOGITS
    F
    6.28
    FF
    6.02
    f
    5.87
    Fs
    5.82
    FK
    5.76
    Fa
    5.67
     FF
    5.59
    fo
    5.57
     F
    5.48
     Fo
    5.44
    Activations Density 0.454%

    No Known Activations