INDEX

Explanations

phrases indicating awards, achievements, or recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ModelState

-0.50

setIsLoading

-0.50

 mier

-0.49

スケ

-0.48

ката

-0.47

rijfs

-0.46

 препратки

-0.46

 nisso

-0.45

komna

-0.44

 schools

-0.44

POSITIVE LOGITS

earned

0.92

 earned

0.91

 attain

0.90

 acquire

0.88

 Obtaining

0.88

 earn

0.86

 attaining

0.86

 Obtain

0.86

 attained

0.85

 صوتيه

0.85

Activations Density 0.388%

phrases indicating awards, achievements, or recognitions

No Comments

No Known Activations