INDEX

Explanations

names and proper nouns related to individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AndEndTag

-0.86

setVerticalGroup

-0.78

DockStyle

-0.66

دانشنامهٔ

-0.62

MigrationBuilder

-0.60

 lenker

-0.60

enterOuterAlt

-0.60

✨:

-0.58

 الحره

-0.57

thood

-0.53

POSITIVE LOGITS

ogenes

0.54

 whips

0.51

bert

0.51

 actionMode

0.51

ชาย

0.50

broad

0.50

InstanceState

0.49

phil

0.49

 webdriver

0.48

fried

0.47

Activations Density 0.216%

names and proper nouns related to individuals

No Comments

No Known Activations