INDEX

Explanations

intensifying adverbs and descriptors that convey strong emotions or perceptions

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

ending in "-ly" or "-ly"-like suffixes

np_acts-logits-general · gemini-2.0-flash

ly adverbs

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

+#+#

-0.96

-0.90

%)$

-0.85

 resourceCulture

-0.85

GEBURTSDATUM

-0.81

 disambiguazione

-0.77

expandindo

-0.77

SBATCH

-0.73

 SwiftUI

-0.72

 Vikipedi

-0.72

POSITIVE LOGITS

ly

4.05

LY

2.50

mente

1.78

fully

1.48

lyt

1.47

ally

1.42

了

1.33

tably

1.33

lye

1.33

nya

1.32

Activations Density 0.476%

intensifying adverbs and descriptors that convey strong emotions or perceptions

ending in "-ly" or "-ly"-like suffixes

ly adverbs

No Comments

No Known Activations