INDEX

Explanations

emphasized phrases expressing strong feelings or opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

-0.56

occasion

-0.56

 occasionally

-0.52

IntegerField

-0.52

 bastante

-0.51

 moderately

-0.50

ardless

-0.50

有一定

-0.49

CharField

-0.49

efty

-0.48

POSITIVE LOGITS

ToScroll

0.84

^(@)

0.79

abestanden

0.78

 amazing

0.78

 itſelf

0.77

 whoſe

0.76

 compac

0.75

 becauſe

0.75

 înc

0.74

 utafitiHapana

0.74

Activations Density 0.072%

emphasized phrases expressing strong feelings or opinions

No Comments

No Known Activations