INDEX

Explanations

terms related to Google APIs and authentication processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RegressionTest

-0.68

kloped

-0.68

+#+#

-0.65

TagMode

-0.64

StoryboardSegue

-0.64

richTextPanel

-0.63

+:+

-0.62

basicConfig

-0.62

oa̍t

-0.61

цездатний

-0.61

POSITIVE LOGITS

 Google

1.73

Google

1.58

 google

1.44

google

1.27

 GOOGLE

1.26

GOOGLE

1.13

谷歌

1.09

 Gmail

0.98

goog

0.98

 goog

0.95

Activations Density 0.338%

terms related to Google APIs and authentication processes

No Comments

No Known Activations