© 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. 1679
    Prev
    Next
    INDEX
    Explanations

    punctuation and transitional phrases within contexts related to discourse or narrative flow

    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
    0:0.12
    1:0.02
    2:0.08
    3:0.03
    4:0.04
    5:0.03
    6:0.25
    7:0.04
    8:0.09
    9:0.19
    10:0.03
    11:0.03
    Negative Logits
    Race
    -4.23
    igl
    -4.04
    race
    -3.70
    uberty
    -3.69
     Race
    -3.64
    Imm
    -3.64
    Sche
    -3.55
    igrants
    -3.52
     rhy
    -3.49
    ��
    -3.44
    POSITIVE LOGITS
     Bent
    10.60
     bent
    5.71
    bent
    5.04
     Bentley
    4.10
     bending
    4.00
     Bung
    3.78
     Tet
    3.74
     tet
    3.71
     Hed
    3.67
     Baxter
    3.65
    Activations Density 0.001%

    No Known Activations