INDEX

Explanations

words and phrases involved in planning events

oai_token-act-pair · gemini-2.0-flash

taking actions

np_max-act · 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

 spesa

-0.53

 WebDriverWait

-0.53

 rospy

-0.52

허

-0.50

 Kirch

-0.48

jero

-0.47

ąt

-0.47

贛

-0.46

 anello

-0.46

 AppColors

-0.45

POSITIVE LOGITS

 BoxFit

0.65

Билгалдахарш

0.62

Искәрмәләр

0.61

 متعلقه

0.58

 виправивши

0.56

ัติ

0.56

 IndexPath

0.56

nologue

0.56

')['

0.54

Expedia

0.52

Activations Density 1.895%

words and phrases involved in planning events

taking actions

No Comments

No Known Activations