INDEX

Explanations

passages related to interviews and reports

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Italijani

-0.74

Aholisi

-0.68

 Италијани

-0.66

])));

-0.65

InputTagHelper

-0.65

ostante

-0.63

LabelTagHelper

-0.62

كويكب

-0.62

contentLoaded

-0.62

 चीज़ों

-0.61

POSITIVE LOGITS

 Reuters

1.12

 Times

1.12

CNN

1.05

BBC

1.05

 Daily

1.05

 CNBC

0.96

 News

0.96

 Bloomberg

0.95

 Newsweek

0.94

The

0.94

Activations Density 0.742%

passages related to interviews and reports

No Comments

No Known Activations