INDEX

Explanations

references to personal accountability and apologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

expandindo

-1.41

tagHelperRunner

-1.15

ValueStyle

-1.03

存于互联网档案馆

-1.03

 виправивши

-1.02

 nahilalakip

-1.01

تقاوى

-0.99

setVerticalGroup

-0.92

出版年

-0.91

 Houſe

-0.91

POSITIVE LOGITS

0.61

0.58

".

0.57

",

0.55

."

0.54

”

0.52

.”

0.51

‘

0.50

Activations Density 0.477%

references to personal accountability and apologies

No Comments

No Known Activations