INDEX

Explanations

words related to government, law, and court cases

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 defaultstate

-0.79

AndEndTag

-0.79

StoryboardSegue

-0.73

DockStyle

-0.72

tagHelperRunner

-0.68

 utafitiHapana

-0.63

 protoimpl

-0.62

 lenker

-0.62

principalTable

-0.61

ksessa

-0.61

POSITIVE LOGITS

<bos>

0.73

send

0.50

"]))

0.48

^{-

0.48

<sup>

0.48

 firma

0.48

<tbody>

0.48

 send

0.47

Send

0.46

vol

0.43

Activations Density 37.441%

words related to government, law, and court cases

No Comments

No Known Activations