INDEX

Explanations

intensifiers or adverbs that emphasize degree or extent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

ded

-0.75

id

-0.74

 Jackman

-0.68

Griffin

-0.65

 проще

-0.64

 ombre

-0.64

zkod

-0.64

ge

-0.63

 Cyclone

-0.63

 Hedges

-0.63

POSITIVE LOGITS

 very

1.39

very

1.31

Very

1.30

 Very

1.29

VERY

1.27

 VERY

1.24

sehr

1.02

Molto

0.97

 très

0.97

muy

0.96

Activations Density 0.070%

intensifiers or adverbs that emphasize degree or extent

No Comments

No Known Activations