© 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. 14972
    Prev
    Next
    INDEX
    Explanations

    the presence of a specific character or symbol repeated in text

    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
    1:0.01
    2:0.05
    3:0.11
    4:0.08
    5:0.23
    6:0.05
    7:0.05
    8:0.07
    9:0.03
    10:0.04
    11:0.18
    Negative Logits
     targ
    -2.96
     juven
    -2.75
    pired
    -2.75
     brill
    -2.71
     NASL
    -2.69
     Nanto
    -2.68
    cellence
    -2.66
    xual
    -2.66
    ndra
    -2.56
     Jiu
    -2.52
    POSITIVE LOGITS
    —
    4.89
    ***
    4.85
    �
    4.62
    ––
    4.55
    §
    4.45
    .—
    4.39
    †
    4.33
    "—
    4.30
    **
    4.30
    —-
    4.20
    Activations Density 0.186%

    No Known Activations