INDEX

Explanations

references to time and duration measures in the text

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

脚注の使い方

-0.73

 '\\;'

-0.70

MENAFN

-0.69

#+#

-0.65

 跳转至

-0.64

nestjs

-0.62

AndEndTag

-0.59



-0.56

SizeMode

-0.55

原始内容存档于

-0.53

POSITIVE LOGITS

 hour

1.32

 minutes

1.09

hour

1.05

 HOUR

1.03

 hours

1.00

 half

0.99

Hour

0.98

 Hour

0.97

 fifteen

0.97

minutes

0.90

Activations Density 0.448%

references to time and duration measures in the text

No Comments

No Known Activations